From Traditional Recommender Systems to GPT-Based Chatbots: A Survey of Recent Developments and Future Directions
[ad_1]
1. Introduction
This survey paper aims to provide an in-depth exploration of the paradigm shift from traditional recommender systems to GPT-based chatbots as recommenders. We aim to offer a comprehensive review of recent developments and emerging trends in this exciting domain, shedding light on the potential advantages and challenges associated with GPT-based solutions. Therefore, the main contributions and unique aspects of our work include:
-
Comprehensive Categorization of Recommender Methods: We provide a comprehensive categorization of various methods utilized to integrate GPT-based chatbots as recommenders. The paper also offers a clear and simplified taxonomy of these different techniques, enabling readers to easily understand and compare the diverse approaches employed in the domain of personalized recommendations.
-
Simplified Presentation of Previous Study Data: In addition to presenting an overview of various techniques, we present data obtained from previous studies in a simplified manner. This simplification facilitates quick comprehension and comparison of the results of prior research, allowing readers to gain valuable insights into the performance of different GPT-based chatbot recommenders.
-
Recommendations and Future Directions for Research: The survey paper concludes by providing informed recommendations and future research directions to enhance the effectiveness of GPT-based chatbots as recommenders. These recommendations are based on the findings of previous studies, serving as a roadmap for future researchers seeking to advance the field of personalized recommendations.
By adopting an engineering perspective, we aim to bring a fresh and innovative approach to the study of recommender systems and GPT-based chatbots, shedding light on the potential advantages and challenges these emerging technologies pose. Our paper aims to be a valuable resource for researchers and practitioners seeking to understand the exciting and dynamic landscape of GPT-based chatbots as recommenders and explore opportunities for further advancements in personalized recommendations.
In this paper, we aim to address the following key research questions:
-
What are the recent developments and emerging trends in leveraging GPT-based chatbots for personalized recommendations?
-
How can GPT models be fine-tuned and adapted to enhance the performance of recommender systems?
-
What are the advantages and limitations of using GPT-based chatbots as recommenders compared to traditional collaborative filtering and content-based approaches?
-
How can GPT-based chatbots facilitate context-aware and interactive recommendations, improving user engagement and satisfaction?
-
What are the potential real-world applications and case studies demonstrating the effectiveness of GPT-based chatbots in recommendation scenarios?
Throughout the paper, we will systematically explore these research questions, providing insights and analyses based on our comprehensive literature review and synthesis of state-of-the-art techniques.
2. Review Methodology and Taxonomy
A systematic and rigorous literature review was conducted to provide a comprehensive overview of the recent developments in GPT-based chatbots for recommender systems.
2.1. Search Strategy, Inclusion/Exclusion Criteria, and Quality Assessment
Search Strategy: A systematic search strategy was employed to conduct a comprehensive review of GPT-based chatbots as recommenders and identify relevant academic papers and articles. The search was performed across various reputable academic databases and more specifically on Google Scholar, Scopus, and IEEE Xplore. Scopus was used first to get an idea of the volume of publications per year and the domains from which they come. The initial search parameter employed in Scopus was “TITLE-ABS-KEY (“chatbot” AND “recommender systems”)”, which returned 134 results. To further narrow down the results, we added the term (“natural language processing” OR “personalized recommendations” OR “GPT”), which resulted in 37 papers. The focus was mainly on peer-reviewed academic journals such as IEEE Xplore, IEEE Transactions, ACM Computing Surveys, AI Magazine published by Wiley, MDPI AI journal, and open-access articles from Springer. Also, various pre-print archiving services, such as arXiv, SSRN, and medRxiv, are included in Scopus. Finally, the search was extended to Google Scholar (with the full query), where we focused on “Review Articles”. The result set included 310 articles.
Inclusion and exclusion criteria: The criteria for the selected papers were as follows:
-
Inclusion criteria
- –
-
Focus on GPT-based chatbot applications in the context of recommender systems.
- –
-
The publication date should be 2010 or later, focusing on the recently published articles in 5 years. However, all the resulting papers from Scopus were published after 2017.
- –
-
Relevance to the research objectives, including discussions on technical aspects, implementation, performance evaluation, and future directions.
- –
-
Investigations that provide insights into recent developments in GPT-based chatbots for recommender systems.
- –
-
Publications available in English.
-
Exclusion Criteria
- –
-
Literature not related to, or does not focus on the application of GPT-based chatbots in recommender systems.
- –
-
Studies that solely explore GPT-based applications in non-recommendation domains.
- –
-
Studies that lack sufficient technical depth.
- –
-
Articles not published in English.
After applying the inclusion and exclusion criteria, the remaining papers were selected for further analysis.
Quality Assessment: The quality of the selected papers was evaluated based on their relevance, methodological rigor, the impact factor of the journals, and citation counts, ensuring the inclusion of credible and significant studies.
2.2. Classification of GPT-Based Chatbots as Recommenders
-
Traditional Recommender Systems: We start by providing an overview of traditional recommender systems, including collaborative filtering, content-based filtering, and hybrid approaches. Key techniques used in traditional recommender systems, such as matrix factorization and singular value decomposition, are explored in detail [20]. Additionally, we address the limitations and challenges faced by traditional recommender systems, including the cold start problem, data sparsity, and scalability issues [21].
-
Emerging Trends in Recommender Systems: The respective section introduces GPT and highlights its transformative capabilities in the field of recommender systems. It discusses the advantages of GPT-based chatbots over traditional approaches, emphasizing their potential to revolutionize personalized recommendations. Moreover, it explores other emerging trends in recommender systems, such as incorporating additional data sources from social media and the Internet of Things (IoT), utilizing multimodal input (e.g., text, images, videos), and leveraging Explainable Artificial Intelligence (XAI) techniques for enhanced transparency and user trust [22].
-
GPT-based Chatbots for Recommendation: Delving deeper into GPT-based chatbots, the respective section examines their application in recommendation tasks. It presents numerous examples of GPT-based chatbots in progress, demonstrating their efficacy in offering personalized suggestions to users. Furthermore, it explores the various ways GPT can be fine-tuned for enhancing recommendation tasks, including prompt engineering and transfer learning. A critical analysis of the strengths and weaknesses of GPT-based chatbots compared to traditional recommender systems sheds light on their potential impact on the field.
-
Case Studies and Real-World Applications: To provide concrete insights, the section presents specific case studies and real-world applications where GPT-based chatbots have been employed in recommendation scenarios. These examples showcase the versatility and effectiveness of GPT-powered systems across diverse domains. Through these case studies, we derive valuable lessons and identify potential avenues for future research and comparative analysis.
This review paper’s methods and taxonomy aim to thoroughly analyze the field of GPT-based chatbots as recommenders, considering various subcategories and recent advancements while maintaining a broader understanding of the technical foundations that underpin these novel systems.
3. Traditional Recommender Systems
In the subsequent sub-sections ahead, we will delve into the intricacies of these traditional methods, uncovering the techniques that underpin their functioning and critically examining their strengths and limitations. This comprehensive understanding will serve as a backdrop for our exploration of the transformative potential of GPT-based chatbots in ushering in a new era of personalized recommendations that transcend the constraints of traditional approaches.
3.1. Types of Traditional Recommender Systems
Traditional recommender systems encompass a spectrum of methodologies, each tailored to address specific recommendation challenges. By understanding these types, we gain insights into the diverse strategies employed in the quest for enhancing user experiences:
-
Collaborative Filtering: Collaborative filtering hinges on the collective behaviors of users to generate recommendations. User-based collaborative filtering identifies users with similar preferences and suggests items enjoyed by others with similar preferences. On the other hand, item-based collaborative filtering identifies similarities among items and recommends those often favored by users who prefer a given item. The strengths of collaborative filtering include its ability to capture complex user preferences and adapt to evolving tastes, solely using the implicit or explicit preferences of users for items captured in a rating or interaction matrix. However, collaborative filtering can face challenges when dealing with sparse data and the cold start problem for new users or items [41,46,47,48,49].
-
Content-Based Filtering: Content-based filtering centers on the intrinsic characteristics of items and users’ historical preferences. By analyzing attributes like item descriptions, genres, and user profile information, this approach can make informed recommendations even when user-item interactions are limited. Content-based filtering excels at tackling the cold start problem, enabling accurate suggestions for new items. However, it may struggle to introduce users to novel or unexpected options due to its reliance on historical preferences [25,41,46,47,50,51].
-
Hybrid Approaches: Hybrid recommender systems combine the strengths of collaborative and content-based filtering to deliver more accurate and diverse recommendations. Rule-based hybrids blend results from multiple recommendation techniques, optimizing their combined benefits. Model-based hybrids integrate different methods within a single model, learning to balance their contributions. Hybrid approaches seek to mitigate the limitations of individual methods, offering improved recommendation quality. However, designing effective hybrid solutions requires careful consideration of model complexity, data availability, and domain-specific challenges [41,46,47,51,52,53].
3.2. Key Techniques in Traditional Recommender Systems
Behind the scenes of traditional recommender systems are foundational techniques that drive recommendation generation and enhance user experience satisfaction. These techniques and algorithms are briefly presented in the following:
-
Matrix Factorization: Matrix factorization involves decomposing the user-item interaction matrix into latent factor matrices. By capturing hidden patterns within the data, matrix factorization uncovers relationships between users and items. This technique enables accurate prediction of missing values, facilitating personalized recommendations. Matrix factorization methods include singular value decomposition (SVD), non-negative matrix factorization (NMF), and probabilistic matrix factorization (PMF) [23,54,55].
-
Singular Value Decomposition: SVD is a widely used matrix factorization technique in recommender systems. It decomposes the user-item interaction matrix into three matrices: the user matrix, the item matrix, and a diagonal matrix of singular values. The resulting latent factors represent user preferences and item attributes. SVD-based methods offer interpretability and reveal underlying dimensions driving user-item interactions [54].
-
Other Techniques: Traditional recommender systems extend beyond matrix factorization to encompass various techniques. Nearest-neighbor methods leverage user/item similarity metrics to make recommendations based on the preferences of similar users or items. Bayesian models combine user preferences with item attributes to predict preferences. Clustering algorithms group users or items with similar behaviors, facilitating recommendation generation [55,56,57].
3.3. Limitations and Challenges
While traditional recommender systems have proven valuable, they encounter inherent limitations that need further attention.
-
Cold-start Problem: The cold start problem surfaces when new users or items lack sufficient interaction history for accurate recommendations. Traditional systems struggle to make relevant suggestions in such scenarios, hindering user satisfaction. Solutions involve leveraging auxiliary data sources or employing hybrid methods to alleviate this challenge [25,41].
-
Scalability Issues: As user bases and item catalogs expand, the scalability of traditional recommender systems becomes a concern. Processing large datasets and maintaining real-time responsiveness demand efficient algorithms and distributed computing frameworks [34].
-
Lack of Personalization: Content-based filtering can lead to over-personalization, where users are confined within their existing preferences, missing out on serendipitous discoveries. Collaborative filtering might fail to capture fine-grained individual tastes, resulting in less precise recommendations. Striking a balance between diversity and relevance remains a persistent challenge [25].
4. Emerging Trends in Recommender Systems
Recommender systems are constantly improving as user needs change and technology advances. New techniques are replacing old ones and transforming personalized recommendations. Recommender systems have made significant progress lately, driven by emerging trends that go beyond incremental improvements. These trends leverage cutting-edge technologies and novel approaches to deliver more accurate and engaging recommendations. From harnessing the prowess of GPT to embracing multimodal input, the following sections highlight the transformative potential of these emerging trends in recommender systems.
4.1. Introduction to GPT and Its Capabilities
4.2. Overview of GPT-Based Chatbots and Their Advantages
4.3. Beyond Item Descriptions and User Profiles: Incorporating Additional Data Sources
4.4. Embracing Multimodal Input for Enhanced Recommendations
4.5. Leveraging XAI Techniques
4.5.1. Techniques for Transparent Recommendations
4.5.2. Enhancing User Trust and Interaction
4.5.3. Addressing Bias and Ethical Considerations
4.5.4. Balancing Complexity and Interpretability
5. GPT-Based Chatbots for Recommendation
In the dynamic landscape of recommender systems, a transformative shift is unfolding with the integration of GPT into conversational agents or recommenders. This section delves into the intersection of advanced NLP and recommendation technology, elucidating how GPT-based chatbots are reshaping user engagement by seamlessly fusing language fluency with personalized suggestions.
This exploration begins with an examination of the GPT model’s fine-tuning techniques tailored for recommendation tasks. We delve into prompt engineering, a process of linguistic calibration that leverages GPT’s linguistic capacity to enhance personalized recommendations. Furthermore, we delve into the domain of transfer learning, exploring how GPT models integrate pre-existing knowledge with recommendation complexities to produce sophisticated recommendations.
5.1. Fine-Tuning GPT for Recommendation Tasks
By exploring these fine-tuning techniques, GPT-based recommendation models can be optimized for recommendation tasks, providing personalized and context-aware suggestions to users. These techniques enhance the linguistic abilities of GPT models, infuse pre-trained knowledge, and enable collaborative training, ultimately improving the quality and effectiveness of recommendations.
5.2. Context-Aware Recommendations with GPT-Based Chatbots
Integrating context-aware recommendations with GPT-based chatbots opens up new possibilities for personalized and engaging interactions. By leveraging the inherent context understanding of GPT models and crafting recommendations that align with ongoing conversations, GPT-based chatbots can provide users with more relevant and tailored suggestions. This context awareness enhances the user experience, increases user satisfaction, and fosters a deeper level of engagement.
5.3. Comparative Analysis: GPT-Based Chatbots vs. Traditional Recommender Systems
6. Case Studies and Real-World Applications
In recent years, there has been a growing interest in AI-driven conversational agents for personalized recommendations. These agents, often powered by advanced language models like GPT-3, can understand and respond to user queries more naturally and context-awarely. This enables them to gather richer information about user preferences, behaviors, and intents through conversations, leading to more accurate and personalized recommendations. Traditional recommendation systems often rely on user behavior and historical data, which can limit capturing the full spectrum of user interests. AI-driven conversational agents can engage users in dynamic conversations, asking clarifying questions and understanding nuances, allowing them to provide recommendations that align with users’ real-time needs and preferences. This trend represents a shift towards more interactive and human-like recommendation experiences, ultimately enhancing user satisfaction and engagement.
Due to the increasing interest in AI-driven conversational agents for personalized recommendations, this section will review relevant works that showcase real case studies of utilizing ChatGPT as a recommender system. These case studies highlight how ChatGPT’s capabilities have been harnessed to create more interactive, context-aware, and human-like recommendation experiences, contributing to the evolution of recommendation systems beyond conventional approaches. By examining these practical implementations, we can gain insights into the effectiveness and potential challenges of using ChatGPT for personalized recommendations in various domains.
6.1. Applications
In the upcoming sub-section, we will delve into the various applications that emerge from utilizing ChatGPT as a recommender system. This examination will illuminate the wide range of contexts and industries in which ChatGPT’s abilities have been successfully utilized to offer individualized and captivating recommendations.
6.1.1. Book Recommendation
6.1.2. Nutrition Recommendation
6.1.3. Healthcare Recommendations
6.1.4. Hotel Recommendation
Furthermore, the study also looked at how persuasive technology might influence user behavior and boost the impact of hotel recommendations. Strategies such as social proof, scarcity, and personalization were examined for their ability to influence user choices and desired behaviors. A pilot study examined how user engagement, satisfaction, and conversion rates were affected by ChatGPT and persuasive strategies. This study featured a hotel recommender system as a case study. The preliminary results highlighted these technologies’ potential to improve guest experiences and business performance. Overall, this research contributed to the hotel hospitality field by delving into the complementary relationship between language models and persuasive technology, with positive implications for guest satisfaction and revenue outcomes.
6.1.5. Emotion Aware Recommendations
6.2. Case Studies
This subsection delves into a collection of case studies exploring how ChatGPT has been employed to enhance recommendation strategies, foster engagement, and drive user satisfaction in various industries and contexts. These case studies give us insights into the transformative power of fusing state-of-the-art language models with recommendation systems, illuminating the path toward more intelligent and empathetic user interactions.
-
Prompt Construction: Tailored prompts are devised following the distinct attributes of the recommendation tasks at hand.
-
Input for ChatGPT: These constructed prompts are furnished as inputs to the ChatGPT model. In response, ChatGPT generates recommendation outcomes in alignment with the guidelines stipulated within the prompts.
-
Refinement of the Output: Within the refinement module, the recommendations generated by ChatGPT are examined and improved. The user is then given the final suggestion results, which are the refined results.
7. Recommendations and Future Directions
In this section, detailed answers, derived from the information and analyses presented in the paper, are provided, demonstrating how the listed research questions have been comprehensively addressed throughout the manuscript.
-
What are the recent developments and emerging trends in leveraging GPT-based chatbots for personalized recommendations?
The paper discusses several recent developments and emerging trends in leveraging GPT-based chatbots for personalized recommendations:
-
Integration of GPT models into conversational agents or chatbots for dynamic and personalized interactions (Section 4.2): “GPT-based chatbots represent a fusion of NLP and recommendation technology, revolutionizing how recommendations are delivered. These chatbots engage users in natural, human-like conversations, enhancing user interaction and personalization [83]”.
-
Incorporation of additional data sources from social media and the IoT to provide contextual recommendations (Section 4.3): “By integrating data from social media interactions, IoT devices, location-based services, and more, these systems gain a holistic view of user context. This contextual understanding empowers recommender systems to deliver recommendations that resonate with users’ real-world experiences [84]”.
-
Embracing multimodal input, such as text, images, and videos, for enhanced recommendations (Section 4.4): “The digital landscape is increasingly multimodal, featuring a fusion of text, images, and videos. This trend has prompted recommender systems to expand their scope beyond text-only interactions. By analyzing and interpreting visual content, these systems gain insights into users’ aesthetic preferences and visual interests [85,86]”.
-
-
How can GPT models be fine-tuned and adapted to enhance the performance of recommender systems?
The paper discusses various techniques for fine-tuning and adapting GPT models to enhance their performance in recommendation tasks:
-
Fine-tuning GPT models on specific recommendation datasets (Section 5.1): “Fine-tuning is a process that involves further training of a generic pre-trained language model, such as GPT, on a specific task or domain to improve its performance. It allows the model to learn from specific recommendation datasets, enabling it to understand the nuances of user preferences and generate more accurate suggestions [17]”.
-
Prompt engineering to guide GPT models to generate relevant recommendations (Section 5.1): “Prompt engineering is a crucial aspect of fine-tuning GPT models for recommendation tasks [87]. It involves designing effective prompts or input formats that elicit the desired recommendation outputs. By carefully crafting prompts, we can guide the model to generate recommendations that align with user preferences and context, enhancing the relevance and personalization of GPT-based recommendations [88]”.
-
Transfer learning to infuse pre-trained knowledge from large-scale language models (Section 5.1): “Transfer learning is another important technique in fine-tuning GPT models for recommendation tasks. It involves infusing pre-trained knowledge from large-scale language models into the recommendation context. By leveraging the pre-trained knowledge, GPT models can benefit from understanding language patterns and semantics, enabling them to generate more coherent and contextually relevant recommendations [89]”.
-
-
What are the advantages and limitations of using GPT-based chatbots as recommenders compared to traditional collaborative filtering and content-based approaches?
The paper discusses both the advantages and limitations of using GPT-based chatbots as recommenders compared to traditional approaches.
-
- –
-
Leverage the power of language models to generate fluent, coherent, and contextually relevant responses, enhancing recommendation quality and user experience.
- –
-
Understand conversational nuances and adapt recommendations based on ongoing interactions, leading to more personalized and tailored suggestions.
- –
-
Potential to address the cold-start problem and provide explainable recommendations.
-
- –
-
Tendency to generate generic or safe responses, impacting the diversity and novelty of recommendations.
- –
-
Requirement for substantial amounts of labeled data for fine-tuning on specific recommendation tasks.
- –
-
Challenges in effectively integrating GPT-based chatbots with existing recommendation models and incorporating user feedback data.
-
-
How can GPT-based chatbots facilitate context-aware and interactive recommendations, improving user engagement and satisfaction?
The paper discusses how GPT-based chatbots can facilitate context-aware and interactive recommendations, improving user engagement and satisfaction:
-
Context-aware recommendations (Section 5.2): “GPT models have demonstrated the ability to comprehend conversational nuances and generate responses that align with ongoing interactions. By utilizing this context understanding, GPT-based chatbots can provide recommendations tailored to the conversation, enhancing the user experience and engagement [90]”.
-
Adapting recommendations based on evolving user context (Section 5.2): “To achieve context-aware recommendations, GPT-based chatbots can adapt their suggestions based on the evolving user context. By continuously analyzing the conversation and understanding the user’s preferences and needs, the chatbot can offer personalized recommendations relevant to the specific context at hand [91]”.
-
Engaging users in natural, human-like conversations (Section 4.2): “GPT-based chatbots engage users in natural, human-like conversations, enhancing user interaction and personalization. Leveraging GPT’s language generation ability, chatbots can offer real-time responses, comprehend user preferences expressed in natural language, and adapt recommendations within the flow of conversation [92,93].”
-
-
What are the potential real-world applications and case studies demonstrating the effectiveness of GPT-based chatbots in recommendation scenarios?
The paper presents several real-world applications and case studies demonstrating the effectiveness of GPT-based chatbots in recommendation scenarios:
-
Book recommendation (Section 6.1.1): The paper discusses the BookGPT framework, which employs ChatGPT for book recommendation tasks such as book rating recommendation, user rating recommendation, and book summary recommendation.
-
Nutrition recommendation (Section 6.1.2): The paper explores the development of NutritionBot, a GPT-powered chatbot that generates personalized pregnancy nutrition recommendations tailored to patients’ lifestyles.
-
Healthcare recommendations (Section 6.1.3): The paper presents case studies where ChatGPT is used to provide medical guidance and recommendations, considering diverse clinical contexts, medical histories, and social characteristics.
-
Hotel recommendation (Section 6.1.4): The paper discusses the integration of ChatGPT and persuasive technologies into hotel hospitality recommender systems, aiming to enhance user engagement, satisfaction, and conversion rates.
-
Emotion-aware recommendations (Section 6.1.5): The paper explores the use of ChatGPT in EARS, employing the AII methodology to quantify and incorporate emotional preferences into recommendations.
-
Moreover, we will address key open research questions in the field of recommender systems. These questions are intended to provide direction for future research efforts and contribute to the progress of recommendation technology.
-
Explainability and Transparency: One central concern revolves around enhancing the explainability and transparency of recommender systems. As recommendation algorithms become more intricate, providing users with comprehensible explanations for their recommendations becomes paramount. Investigating techniques to generate interpretable explanations and develop transparent recommendation models is essential to fostering user trust and satisfaction [94,95].
-
Ethical Considerations: Ethical considerations in recommender systems present another significant challenge. These systems can significantly influence user behavior and preferences, necessitating a focus on issues such as fairness, diversity, and privacy in recommendation algorithms. Research should concentrate on developing fair and unbiased recommendation models, ensuring diversity in recommendations, and safeguarding user privacy [96].
-
Contextual Recommendations: Improving contextual recommendations is a pivotal research direction. Context profoundly influences user preferences and decision-making. Incorporating contextual information, such as time, location, and social context, into recommendation algorithms can enhance the relevance and effectiveness of recommendations. Investigating techniques to capture and utilize contextual information in recommender systems is an important research direction [97].
-
Long-Term User Modeling: The construction of long-term user models is another key area of interest in recommender systems. User preferences evolve over time, requiring recommender systems to adapt accordingly. Developing user modeling techniques capable of capturing long-term user behavior and preferences can lead to more accurate and personalized recommendations. Research in this area should explore methods for modeling user preferences over extended periods and incorporating temporal dynamics into recommendation algorithms [98].
-
Cross-Domain Recommendations: Enhancing cross-domain recommendations presents an intriguing challenge. Recommender systems often focus on specific domains, yet users have diverse interests spanning multiple areas. Investigating techniques for effectively recommending items across different domains and addressing the challenges of data sparsity and domain adaptation are critical research directions [99].
These open research questions provide a foundation for future investigations in the field of recommender systems. By addressing these challenges, we can advance the state-of-the-art in recommendation technologies and improve user experiences in various domains. Recommender systems have become integral in our daily lives, guiding us to relevant information, products, and services. However, several open questions and challenges remain, requiring further research to enhance the effectiveness and usability of these systems.
8. Conclusions
In conclusion, this survey paper has comprehensively explored the paradigm shift from traditional recommender systems to GPT-based chatbots as recommenders. Through a systematic review methodology and taxonomy, we have examined the diverse landscape of GPT-powered solutions in the context of personalized recommendations.
The discussion on GPT-based chatbots for recommendation tasks offered insights into their applications, fine-tuning methods, and a critical analysis of their strengths and weaknesses compared to traditional systems. By examining specific case studies and real-world applications, we demonstrated the versatility and potential impact of GPT-powered solutions in diverse recommendation domains.
We have also provided detailed answers to the research questions posed in this study. By addressing these research questions and providing valuable insights into the applications and implications of GPT-based chatbots in personalized recommendations, this survey paper contributes to the evolving landscape of recommendation systems and sets the stage for future advancements in this dynamic field.
As a result of our survey, we identified open research questions and presented potential future directions. These recommendations provide researchers with valuable insights to further explore new GPT architectures, training methods, the integration of several additional modalities, and ethical considerations in recommender systems.
Overall, this survey paper underscores the significance of GPT-based chatbots as game-changers in personalized recommendations. As the field continues to evolve rapidly, we believe that GPT-powered solutions hold the promise of redefining user experiences in various domains, from e-commerce to content streaming platforms. The seamless integration of GPT technology with traditional recommender systems showcases the potential for creating more contextually relevant and engaging user experiences.
This survey paper provides a thorough knowledge of GPT-based chatbots as recommenders and serves as a significant resource for scholars and practitioners in the rapidly evolving field of AI and recommender systems. It also encourages additional study and innovation in this fascinating field. As we look towards the future, we call upon the research community to collaborate and push the boundaries of GPT-based solutions, ultimately advancing the state-of-the-art in personalized recommendations for users worldwide.
Author Contributions
Conceptualization, T.M.A.-H., A.N.S., F.B., Y.H., I.V. and G.D.; Formal Analysis, T.M.A.-H. and A.N.S.; Methodology, T.M.A.-H., A.N.S. and F.B.; Writing—Original Draft Preparation, T.M.A.-H. and A.N.S.; Writing—Review and Editing, T.M.A.-H., A.N.S., F.B., Y.H., I.V. and G.D.; Visualization, T.M.A.-H. and A.N.S.; Supervision, F.B., Y.H., I.V. and G.D.; Project Administration, F.B.; Funding Acquisition, F.B. All authors have read and agreed to the published version of the manuscript.
Funding
This research was funded by the National Priorities Research Programme (NPRP) with grant № (NPRP14S-0401-210122) by Qatar National Research Fund of Qatar Foundation.
Data Availability Statement
No new data were created or analyzed in this study. Data sharing is not applicable to this article.
Acknowledgments
This publication was made possible by the National Priorities Research Programme (NPRP) award [NPRP14S-0401-210122] from the Qatar National Research Fund (a member of The Qatar Foundation). The statements made herein are solely the responsibility of the authors.
Conflicts of Interest
The authors declare no conflicts of interest nor personal or financial relationships impacting this work.
References
- Regàs, B.I. Recommendatory System for Supermarket Online Shopping. Master’s Thesis, Universitat Politècnica de Catalunya, Barcelona, Spain, 2022. [Google Scholar]
- Gao, Y.; Sheng, T.; Xiang, Y.; Xiong, Y.; Wang, H.; Zhang, J. Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv 2023, arXiv:2303.14524. [Google Scholar]
- Li, Y.; Tan, Z.; Liu, Y. Privacy-Preserving Prompt Tuning for Large Language Model Services. arXiv 2023, arXiv:2305.06212. [Google Scholar]
- Sayed, A.; Himeur, Y.; Alsalemi, A.; Bensaali, F.; Amira, A. Intelligent edge-based recommender system for internet of energy applications. IEEE Syst. J. 2021, 16, 5001–5010. [Google Scholar] [CrossRef]
- Varlamis, I.; Sardianos, C.; Dimitrakopoulos, G.; Alsalemi, A.; Bensaali, F.; Himeur, Y.; Amira, A. Rehab-c: Recommendations for energy habits change, future generation computer systems. Future Gener. Comput. Syst. 2020, 112, 394–407. [Google Scholar]
- Geng, S.; Liu, S.; Fu, Z.; Ge, Y.; Zhang, Y. Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5). In Proceedings of the 16th ACM Conference on Recommender Systems, Seattle, WA, USA, 18–23 September 2022; pp. 299–315. [Google Scholar]
- Himeur, Y.; Alsalemi, A.; Al-Kababji, A.; Bensaali, F.; Amira, A.; Sardianos, C.; Dimitrakopoulos, G.; Varlamis, I. A survey of recommender systems for energy efficiency in buildings: Principles, challenges and prospects. Inf. Fusion 2021, 72, 1–21. [Google Scholar] [CrossRef]
- Yannam, V.R.; Kumar, J.; Babu, K.S.; Sahoo, B. Improving group recommendation using deep collaborative filtering approach. Int. J. Inf. Technol. 2023, 15, 1489–1497. [Google Scholar] [CrossRef]
- Kumari, T.S.; Sagar, K. A Semantic Approach to Solve Scalability, Data Sparsity and Cold-Start Problems in Movie Recommendation Systems. Int. J. Intell. Syst. Appl. Eng. 2023, 11, 825–837. [Google Scholar]
- Sohail, S.S.; Farhat, F.; Himeur, Y.; Nadeem, M.; Madsen, D.Ø.; Singh, Y.; Atalla, S.; Mansoor, W. Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions. J. King Saud-Univ. Inf. Sci. 2023, 35, 101675. [Google Scholar]
- Rima, S.; Meriem, H.; Najima, D.; Rachida, A. Toward a Generative Chatbot for an OER Recommender System Designed for the Teaching Community: General Architecture and Technical Components. In Proceedings of the International Conference on Artificial Intelligence and Computer Vision, Marrakesh, Morocco, 5–7 March 2023; pp. 348–357. [Google Scholar]
- Omara, J.; Talavera, E.; Otim, D.; Turcza, D.; Ofumbi, E.; Owomugisha, G. A field-based recommender system for crop disease detection using machine learning. Front. Artif. Intell. 2023, 6, 1010804. [Google Scholar] [CrossRef]
- Goktas, P.; Karakaya, G.; Kalyoncu, A.F.; Damadoglu, E. Artificial Intelligence Chatbots in Allergy and Immunology Practice: Where Have We Been and Where Are We Going? J. Allergy Clin. Immunol. Pract. 2023, 11, 2697–2700. [Google Scholar] [CrossRef]
- Sohail, S.S.; Farhat, F.; Himeur, Y.; Nadeem, M.; Madsen, D.Ø.; Singh, Y.; Atalla, S.; Mansoor, W. The Future of GPT: A Taxonomy of Existing ChatGPT Research, Current Challenges, and Possible Future Directions. SSRN 2023. [Google Scholar] [CrossRef]
- Pathak, A. Exploring ChatGPT: An Extensive Examination of its Background, Applications, Key Challenges, Bias, Ethics, Limitations, and Future Prospects. SSRN 2023. [Google Scholar] [CrossRef]
- Deldjoo, Y. Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency. arXiv 2024, arXiv:2401.10545. [Google Scholar]
- Spurlock, K.D.; Acun, C.; Saka, E.; Nasraoui, O. ChatGPT for Conversational Recommendation: Refining Recommendations by Reprompting with Feedback. arXiv 2024, arXiv:2401.03605. [Google Scholar]
- Wang, Z. Empowering Few-Shot Recommender Systems with Large Language Models-Enhanced Representations. IEEE Access 2024, 12, 29144–29153. [Google Scholar] [CrossRef]
- Xu, L.; Zhang, J.; Li, B.; Wang, J.; Cai, M.; Zhao, W.X.; Wen, J.R. Prompting Large Language Models for Recommender Systems: A Comprehensive Framework and Empirical Analysis. arXiv 2024, arXiv:2401.04997. [Google Scholar]
- Varlamis, I.; Sardianos, C.; Chronis, C.; Dimitrakopoulos, G.; Himeur, Y.; Alsalemi, A.; Bensaali, F.; Amira, A. Using big data and federated learning for generating energy efficiency recommendations. Int. J. Data Sci. Anal. 2022, 16, 353–369. [Google Scholar] [CrossRef]
- Alsalemi, A.; Himeur, Y.; Bensaali, F.; Amira, A.; Sardianos, C.; Varlamis, I.; Dimitrakopoulos, G. Achieving domestic energy efficiency using micro-moments and intelligent recommendations. IEEE Access 2020, 8, 15047–15055. [Google Scholar] [CrossRef]
- Sardianos, C.; Varlamis, I.; Chronis, C.; Dimitrakopoulos, G.; Alsalemi, A.; Himeur, Y.; Bensaali, F.; Amira, A. The emergence of explainability of intelligent systems: Delivering explainable and personalized recommendations for energy efficiency. Int. J. Intell. Syst. 2021, 36, 656–680. [Google Scholar] [CrossRef]
- Herlocker, J.L.; Konstan, J.A.; Terveen, L.G.; Riedl, J.T. Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. 2004, 22, 5–53. [Google Scholar] [CrossRef]
- Tharwat, M.; Jacob, D.W.; Fudzee, M.F.M.; Kasim, S.; Ramli, A.A.; Lubis, M. The role of trust to enhance the recommendation system based on social network. Int. J. Adv. Sci. Eng. Inf. Technol. 2020, 10, 1387–1395. [Google Scholar] [CrossRef]
- Lee, Y.; Jung, Y. A Mapping Approach to Identify Player Types for Game Recommendations. Information 2019, 10, 379. [Google Scholar] [CrossRef]
- Natarajan, S.; Vairavasundaram, S.; Natarajan, S.; Gandomi, A.H. Resolving data sparsity and cold start problem in collaborative filtering recommender system using linked open data. Expert Syst. Appl. 2020, 149, 113248. [Google Scholar] [CrossRef]
- Ye, H.; Li, X.; Yao, Y.; Tong, H. Towards robust neural graph collaborative filtering via structure denoising and embedding perturbation. ACM Trans. Inf. Syst. 2023, 41, 1–28. [Google Scholar] [CrossRef]
- Xia, L.; Huang, C.; Shi, J.; Xu, Y. Graph-less collaborative filtering. In Proceedings of the ACM Web Conference 2023, Austin, TX, USA, 30 April–4 May 2023; pp. 17–27. [Google Scholar]
- Xu, S.; Tan, J.; Heinecke, S.; Li, V.J.; Zhang, Y. Deconfounded causal collaborative filtering. ACM Trans. Recomm. Syst. 2023, 1, 1–25. [Google Scholar] [CrossRef]
- Jozani, M.; Liu, C.Z.; Choo, K.K.R. An empirical study of content-based recommendation systems in mobile app markets. Decis. Support Syst. 2023, 169, 113954. [Google Scholar] [CrossRef]
- Mishan, M.T.; Amir, A.L.; Supir, M.H.B.M.; Kushan, A.L.; Zulkifli, N.; Rahmat, M.H. Integrating Business Intelligence and Recommendation Marketplace System for Hawker Using Content Based Filtering. In Proceedings of the 2023 4th International Conference on Artificial Intelligence and Data Sciences (AiDAS), Ipoh, Malaysia, 6–7 September 2023; pp. 200–205. [Google Scholar]
- Nosrati, V.; Rahmani, M.; Jolfaei, A.; Seifollahi, S. A Weak-Region Enhanced Bayesian Classification for Spam Content-Based Filtering. ACM Trans. Asian-Low Lang. Inf. Process. 2023, 22, 1–18. [Google Scholar] [CrossRef]
- El-Shaikh, A.; Seeger, B. Content-based filter queries on DNA data storage systems. Sci. Rep. 2023, 13, 7053. [Google Scholar] [CrossRef]
- Ikhsanudin, R.; Winarko, E. Parallelization of Hybrid Content Based and Collaborative Filtering Method in Recommendation System with Apache Spark. IJCCS Indones. J. Comput. Cybern. Syst. 2019, 13, 149–158. [Google Scholar] [CrossRef]
- Patro, S.G.K.; Mishra, B.K.; Panda, S.K.; Kumar, R.; Long, H.V.; Taniar, D. Cold start aware hybrid recommender system approach for E-commerce users. Soft Comput. 2023, 27, 2071–2091. [Google Scholar] [CrossRef]
- Chen, C.C.; Lai, P.L.; Chen, C.Y. ColdGAN: An effective cold-start recommendation system for new users based on generative adversarial networks. Appl. Intell. 2023, 53, 8302–8317. [Google Scholar] [CrossRef]
- Nazari, A.; Kordabadi, M.; Mansoorizadeh, M. Scalable and Data-Independent Multi-Agent Recommender System Using Social Networks Analysis. Int. J. Inf. Technol. Decis. Mak. 2023, 1–22. [Google Scholar] [CrossRef]
- Hu, H.; Dobbie, G.; Salcic, Z.; Liu, M.; Zhang, J.; Lyu, L.; Zhang, X. Differentially private locality sensitive hashing based federated recommender system. Concurr. Comput. Pract. Exp. 2023, 35, e6233. [Google Scholar] [CrossRef]
- Idrissi, N.; Zellou, A. A systematic literature review of sparsity issues in recommender systems. Soc. Netw. Anal. Min. 2020, 10, 15. [Google Scholar] [CrossRef]
- Salas, J. Sanitizing and measuring privacy of large sparse datasets for recommender systems. J. Ambient. Intell. Humaniz. Comput. 2023, 14, 15073–15084. [Google Scholar] [CrossRef]
- Choi, S.M.; Jang, K.; Lee, T.D.; Khreishah, A.; Noh, W. Alleviating item-side cold-start problems in recommender systems using weak supervision. IEEE Access 2020, 8, 167747–167756. [Google Scholar] [CrossRef]
- Chaimalas, I.; Walker, D.M.; Gruppi, E.; Clark, B.R.; Toni, L. Bootstrapped personalized popularity for cold start recommender systems. In Proceedings of the 17th ACM Conference on Recommender Systems, Singapore, 18–22 September 2023; pp. 715–722. [Google Scholar]
- Kalla, D.; Smith, N.; Samaah, F.; Polimetla, K. Hybrid Scalable Researcher Recommendation System Using Azure Data Lake Analytics. J. Data Anal. Inf. Process. 2024, 12, 76–88. [Google Scholar] [CrossRef]
- Rajput, S.; Mehta, N.; Singh, A.; Hulikal Keshavan, R.; Vu, T.; Heldt, L.; Hong, L.; Tay, Y.; Tran, V.; Samost, J.; et al. Recommender systems with generative retrieval. Adv. Neural Inf. Process. Syst. 2024, 36, 10299–10315. [Google Scholar]
- Alkan, O.; Daly, E.M.; Botea, A. An evaluation framework for interactive recommender systems. In Proceedings of the Adjunct Publication of the 27th Conference on User Modeling, Adaptation and Personalization, Larnaca, Cyprus, 9–12 June 2019; pp. 217–218. [Google Scholar]
- Zahra, S.; Ghazanfar, M.A.; Khalid, A.; Azam, M.A.; Naeem, U.; Prugel-Bennett, A. Novel centroid selection approaches for KMeans-clustering based recommender systems. Inf. Sci. 2015, 320, 156–189. [Google Scholar] [CrossRef]
- Safoury, L.; Salah, A. Exploiting User Demographic Attributes for Solving Cold-Start Problem in Recommender System. Lect. Notes Softw. Eng. 2013, 1, 303–307. [Google Scholar] [CrossRef]
- Hansel, A.C.; Wibowo, A. Using Movie Genres in Neural Network Based Collaborative Filtering Movie Recommendation System to Reduce Cold Start Problem. Int. J. Emerg. Technol. Adv. Eng. 2022, 12, 63–73. [Google Scholar] [CrossRef]
- Vairachilai, S.; Kavithadevi, M.K.; Raja, M. Alleviating the Cold Start Problem in Recommender Systems Based on Modularity Maximization Community Detection Algorithm. Circuits Syst. 2016, 7, 1268–1279. [Google Scholar] [CrossRef]
- Fan, Z.; Burgun, E.; Schleyer, T.; Ning, X. Improving information retrieval from electronic health records using dynamic and multi-collaborative filtering. In Proceedings of the 2019 IEEE International Conference on Healthcare Informatics (ICHI), Xi’an, China, 10–13 June 2019. [Google Scholar] [CrossRef]
- Anthony Jnr, B. A case-based reasoning recommender system for sustainable smart city development. AI Society 2021, 36, 159–183. [Google Scholar] [CrossRef]
- Vaz, P.C.; de Matos, D.M.; Martins, B.; Calado, P. Improving a hybrid literary book recommendation system through author ranking. In Proceedings of the 12th ACM/IEEE-CS Joint Conference on Digital Libraries, ACM, Washington, DC, USA, 10–14 June 2012. [Google Scholar] [CrossRef]
- Li, X.; Li, D. An Improved Collaborative Filtering Recommendation Algorithm and Recommendation Strategy. Mob. Inf. Syst. 2019, 2019, 1–11. [Google Scholar] [CrossRef]
- Liu, Y.; Huang, F.; Xie, X.; Huang, H. Research on Singular Value Decomposition Recommendation Algorithm Based on Data Filling. Int. J. Inf. Technol. Syst. Approach 2023, 16, 1–15. [Google Scholar] [CrossRef]
- Bin, S.; Sun, G. Matrix factorization recommendation algorithm based on multiple social relationships. Math. Probl. Eng. 2021, 2021, 6610645. [Google Scholar] [CrossRef]
- Mann, S.K.; Chawla, S. Cluster-Based Cab Recommender System (CBCRS) for Solo Cab Drivers. Int. J. Inf. Retr. Res. 2022, 12, 1–15. [Google Scholar] [CrossRef]
- Wan, P. Development of the Employment Recommendation System based on K-Means Improved Collaborative Filtering Algorithm. In Proceedings of the 2022 2nd International Conference on Management Science and Software Engineering (ICMSSE 2022), Chengdu, China, 24–26 June 2022; pp. 489–494. [Google Scholar]
- Devlin, J.; Chang, M.W.; Lee, K.; Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv 2018, arXiv:1810.04805. [Google Scholar]
- Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 2020, 33, 1877–1901. [Google Scholar]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30, 6000–6010. [Google Scholar]
- Zhang, S.; Yao, L.; Sun, A.; Tay, Y. Deep learning based recommender system: A survey and new perspectives. ACM Comput. Surv. (CSUR) 2019, 52, 1–38. [Google Scholar] [CrossRef]
- Zou, J.; Thoma, G.; Antani, S. Unified deep neural network for segmentation and labeling of multipanel biomedical figures. J. Assoc. Inf. Sci. Technol. 2020, 71, 1327–1340. [Google Scholar] [CrossRef]
- Eggl, E.; Schleede, S.; Bech, M.; Achterhold, K.; Loewen, R.; Ruth, R.D.; Pfeiffer, F. X-ray phase-contrast tomography with a compact laser-driven synchrotron source. Proc. Natl. Acad. Sci. USA 2015, 112, 5567–5572. [Google Scholar] [CrossRef] [PubMed]
- Joseph, M.; Kearns, M.; Morgenstern, J.H.; Roth, A. Fairness in learning: Classic and contextual bandits. Adv. Neural Inf. Process. Syst. 2016, 29, 1–9. [Google Scholar]
- Li, Y.; Chen, H.; Xu, S.; Ge, Y.; Zhang, Y. Personalized Counterfactual Fairness in Recommendation. arXiv 2021, arXiv:2105.09829. [Google Scholar]
- Fan, W.; Zhao, Z.; Li, J.; Liu, Y.; Mei, X.; Wang, Y.; Tang, J.; Li, Q. Recommender systems in the era of large language models (LLMs). arXiv 2023, arXiv:2307.02046. [Google Scholar]
- Yang, Z.; Dai, Z.; Yang, Y.; Carbonell, J.; Salakhutdinov, R.R.; Le, Q.V. Xlnet: Generalized autoregressive pretraining for language understanding. Adv. Neural Inf. Process. Syst. 2019, 32, 11. [Google Scholar]
- Konečnỳ, J.; McMahan, H.B.; Yu, F.X.; Richtárik, P.; Suresh, A.T.; Bacon, D. Federated learning: Strategies for improving communication efficiency. arXiv 2016, arXiv:1610.05492. [Google Scholar]
- Li, J.; Galley, M.; Brockett, C.; Gao, J.; Dolan, B. A diversity-promoting objective function for neural conversation models. arXiv 2015, arXiv:1510.03055. [Google Scholar]
- Zhang, S.; Dinan, E.; Urbanek, J.; Szlam, A.; Kiela, D.; Weston, J. Personalizing dialogue agents: I have a dog, do you have pets too? arXiv 2018, arXiv:1801.07243. [Google Scholar]
- Panda, S.; Kaur, N. Exploring the viability of ChatGPT as an alternative to traditional chatbot systems in library and information centers. Libr. Hi Tech News 2023, 40, 22–25. [Google Scholar] [CrossRef]
- Zhiyuli, A.; Chen, Y.; Zhang, X.; Liang, X. BookGPT: A General Framework for Book Recommendation Empowered by Large Language Model. arXiv 2023, arXiv:2305.15673. [Google Scholar]
- Lappalainen, Y.; Narayanan, N. Aisha: A Custom AI Library Chatbot Using the ChatGPT API. J. Web Librariansh. 2023, 27, 223–231. [Google Scholar] [CrossRef]
- Tsai, C.H.; Kadire, S.; Sreeramdas, T.; VanOrmer, M.; Thoene, M.; Hanson, C.; Berry, A.A.; Khazanchi, D. Generating Personalized Pregnancy Nutrition Recommendations with GPT-Powered AI Chatbot. In Proceedings of the 20th International Conference on Information Systems for Crisis Response and Management (ISCRAM), Omaha, NE, USA, 28 May–31 May 2023; Volume 2023, p. 263. [Google Scholar]
- Nastasi, A.J.; Courtright, K.R.; Halpern, S.D.; Weissman, G.E. Does ChatGPT provide appropriate and equitable medical advice?: A vignette-based, clinical evaluation across care contexts. medRxiv 2023. [Google Scholar] [CrossRef]
- Thawkar, O.; Shaker, A.; Mullappilly, S.S.; Cholakkal, H.; Anwer, R.M.; Khan, S.; Laaksonen, J.; Khan, F.S. Xraygpt: Chest radiographs summarization using medical vision-language models. arXiv 2023, arXiv:2306.07971. [Google Scholar]
- Remountakis, M.; Kotis, K.; Kourtzis, B.; Tsekouras, G.E. ChatGPT and Persuasive Technologies for the Management and Delivery of Personalized Recommendations in Hotel Hospitality. arXiv 2023, arXiv:2307.14298. [Google Scholar]
- Leung, J.K.; Griva, I.; Kennedy, W.G.; Kinser, J.M.; Park, S.; Lee, S.Y. The Application of Affective Measures in Text-based Emotion Aware Recommender Systems. arXiv 2023, arXiv:2305.04796. [Google Scholar]
- Liu, J.; Liu, C.; Lv, R.; Zhou, K.; Zhang, Y. Is chatgpt a good recommender? a preliminary study. arXiv 2023, arXiv:2304.10149. [Google Scholar]
- Li, J.; Zhang, W.; Wang, T.; Xiong, G.; Lu, A.; Medioni, G. GPT4Rec: A generative framework for personalized recommendation and user interests interpretation. arXiv 2023, arXiv:2304.03879. [Google Scholar]
- Dai, S.; Shao, N.; Zhao, H.; Yu, W.; Si, Z.; Xu, C.; Sun, Z.; Zhang, X.; Xu, J. Uncovering ChatGPT’s Capabilities in Recommender Systems. arXiv 2023, arXiv:2305.02182. [Google Scholar]
- Rivas, P.; Zhao, L. Marketing with chatgpt: Navigating the ethical terrain of gpt-based chatbot technology. AI 2023, 4, 375–384. [Google Scholar] [CrossRef]
- Ha, J.; Jeon, H.; Han, D.; Seo, J.; Oh, C. CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models. arXiv 2024, arXiv:2402.15265. [Google Scholar]
- Bansal, G.; Chamola, V.; Hussain, A.; Guizani, M.; Niyato, D. Transforming Conversations with AI—A Comprehensive Study of ChatGPT. Cogn. Comput. 2024, 1, 1–24. [Google Scholar] [CrossRef]
- Martins, A.; Nunes, I.; Lapão, L.; Londral, A. Unlocking Human-Like Conversations: Scoping Review of Automation Techniques for Personalized Healthcare Interventions using Conversational Agents. Int. J. Med. Inform. 2024, 1, 105385. [Google Scholar] [CrossRef]
- Wang, P.; Wei, X.; Hu, F.; Han, W. TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation. arXiv 2024, arXiv:2402.07233. [Google Scholar]
- Feng, S.; Chen, C. Prompting Is All You Need: Automated Android Bug Replay with Large Language Models. In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering, Lisbon, Portugal, 14–20 April 2024; pp. 1–13. [Google Scholar]
- Wu, Y.; Xie, R.; Zhu, Y.; Zhuang, F.; Zhang, X.; Lin, L.; He, Q. Personalized Prompt for Sequential Recommendation. IEEE Trans. Knowl. Data Eng. 2024; early Access. [Google Scholar]
- Wang, C.; Chen, T.; Liu, Y.; Kang, M.; Su, S.; Li, B. TransMI: A transfer-learning method for generalized map information evaluation. Cartogr. Geogr. Inf. Sci. 2024, 1, 1–17. [Google Scholar] [CrossRef]
- Zhang, H.; Cheah, Y.N.; Alyasiri, O.M.; An, J. Exploring aspect-based sentiment quadruple extraction with implicit aspects, opinions, and ChatGPT: A comprehensive survey. Artif. Intell. Rev. 2024, 57, 17. [Google Scholar] [CrossRef]
- Kim, M.; Adlof, L. Adapting to the Future: ChatGPT as a Means for Supporting Constructivist Learning Environments. TechTrends 2024, 68, 37–46. [Google Scholar] [CrossRef]
- Bansal, R. Unveiling the Potential of ChatGPT for Enhancing Customer Engagement. In Leveraging ChatGPT and Artificial Intelligence for Effective Customer Engagement; IGI Global: Hershey, PE, USA, 2024; pp. 111–128. [Google Scholar]
- Khan, R.; Khan, S.P.; Ali, S.A. Conversational AI: Dialoguing Most Humanly with Non-Humans. In Conversational Artificial Intelligence; Rawat, R., Chakrawarti, R.K., Sarangi, S.K., Vyas, P., Alamanda, M.S., Srividya, K., Sankaran, K.S., Eds.; Scrivener Publishing LLC: Beverly, MA, USA, 2024; pp. 249–268. [Google Scholar]
- Krishna, S.; Ma, J.; Slack, D.; Ghandeharioun, A.; Singh, S.; Lakkaraju, H. Post hoc explanations of language models can improve language models. Adv. Neural Inf. Process. Syst. 2024, 36, 65468–65483. [Google Scholar]
- Wang, X.; Li, Q.; Yu, D.; Li, Q.; Xu, G. Reinforced path reasoning for counterfactual explainable recommendation. IEEE Trans. Knowl. Data Eng. 2024; early access. [Google Scholar]
- Stahl, B.C.; Eke, D. The ethics of ChatGPT–Exploring the ethical issues of an emerging technology. Int. J. Inf. Manag. 2024, 74, 102700. [Google Scholar] [CrossRef]
- Lim, D.Y.Z.; Tan, Y.B.; Koh, J.T.E.; Tung, J.Y.M.; Sng, G.G.R.; Tan, D.M.Y.; Tan, C.K. ChatGPT on guidelines: Providing contextual knowledge to GPT allows it to provide advice on appropriate colonoscopy intervals. J. Gastroenterol. Hepatol. 2024, 39, 81–106. [Google Scholar] [CrossRef]
- Wen, X.; Nie, W.; Liu, J.; Su, Y.; Zhang, Y.; Liu, A.A. CDCM: ChatGPT-Aided Diversity-Aware Causal Model for Interactive Recommendation. IEEE Trans. Multimed. 2024; early access. [Google Scholar]
- Ma, H.; Xie, R.; Meng, L.; Chen, X.; Zhang, X.; Lin, L.; Zhou, J. Triple sequence learning for cross-domain recommendation. ACM Trans. Inf. Syst. 2024, 42, 91. [Google Scholar] [CrossRef]
Figure 1.
Flowchart illustrating how papers were systematically selected for the survey.
Figure 1.
Flowchart illustrating how papers were systematically selected for the survey.
Figure 2.
Year of publication of the reviewed papers.
Figure 2.
Year of publication of the reviewed papers.
Figure 3.
PRISMA flow diagram illustrating the systematic selection process.
Figure 3.
PRISMA flow diagram illustrating the systematic selection process.
Figure 4.
Dimensions of recommender systems.
Figure 4.
Dimensions of recommender systems.
Figure 5.
Basic diagram and classification of traditional recommender systems based on the user and content relation.
Figure 5.
Basic diagram and classification of traditional recommender systems based on the user and content relation.
Figure 6.
Potential multimodal biomedical AI data modalities and opportunities.
Figure 6.
Potential multimodal biomedical AI data modalities and opportunities.
Figure 7.
Overview of the sequence of steps for employing ChatGPT to execute five recommendation tasks and evaluate recommendations’ quality.
Figure 7.
Overview of the sequence of steps for employing ChatGPT to execute five recommendation tasks and evaluate recommendations’ quality.
Table 1.
Comparison of traditional recommender systems.
Table 1.
Comparison of traditional recommender systems.
Aspect | Collaborative Filtering | Content-Based Filtering | Hybrid Approaches |
---|---|---|---|
Technique | User/item similarity | Item characteristics | Combines both |
Strengths | Captures complex user preferences, adapts to evolving tastes | Tackles cold start problem, provides accurate suggestions for new items | Balances collaborative and content-based filtering, offers improved recommendation quality |
Challenges | Sparse data, cold start problem for new users/items | Limited novelty, reliance on historical preferences | Model complexity, data availability, domain-specific challenges |
Scalability | Scales well with large user/item datasets, can be parallelized for efficiency | Scalable to large item catalogs, efficient for large datasets | Scalability depends on hybridization approach, complexity |
Interpretability | User behavior-driven, harder to explain recommendations | Easy to explain based on item attributes | Interpretability varies based on hybrid approach |
Diversity | Can struggle to provide diverse recommendations, may lead to filter bubbles | Offers diverse recommendations based on item attributes | Aims to balance diversity and relevance |
Adaptability | Adapts to evolving user preferences over time | Less adaptable to changing user tastes | Adaptability depends on hybridization approach |
Novelty | Might not recommend entirely new items to users | More likely to introduce users to novel options | Strives for a balance between familiarity and novelty |
Data Requirements | Relies on historical user-item interactions | Requires item attribute data and user preferences | Data requirements vary based on hybrid approach |
Explanation | May lack explainability in recommendations | Can provide clear explanations based on item attributes | Explanation varies based on hybrid approach |
Handling Sparsity | Sensitive to data sparsity issues | Less sensitive to data sparsity, thanks to item attributes | Handling sparsity depends on hybridization approach |
Table 2.
Emerging trends in recommender systems.
Table 2.
Emerging trends in recommender systems.
Trend | Description | Applications and Benefits | Reference Works |
---|---|---|---|
GPT-Based Chatbots | Integration of GPT models into chatbots for dynamic and personalized interactions. | Enhanced user engagement, natural language conversations, and immersive recommendation experiences. | [59,60] |
Multimodal Recommendations | Incorporation of visual content analysis into recommendations. | Improved recommendation accuracy, relevance, and user experience, especially in domains like e-commerce and healthcare. | [60,61] |
Contextual Understanding | Utilization of contextual information from diverse sources, including social media and IoT data. | Recommendations aligned with users’ real-world experiences, expanding the scope beyond historical preferences. | [60] |
XAI Techniques | Implementation of XAI techniques for transparent and trustworthy recommendations. | User trust, fairness, bias mitigation, and ethical considerations addressed, fostering informed decision-making. | [22,61,64,65] |
Table 3.
Summary of recent GPT-based chatbots utilized as recommender systems in various applications.
Table 3.
Summary of recent GPT-based chatbots utilized as recommender systems in various applications.
Work | Approach | Dataset | Application | Performance | Advantage/Limitation |
---|---|---|---|---|---|
BookGPT [72] (2023) | Douban, Wenxin and ChatGPT 3.5 | N/A | Online Shopping | Book recommendation | BookGPT shows promise in multiple types of recommendation tasks, displaying a wide range of utility within the book recommendation ecosystem. |
Aisha [73] | ChatGPT API | Education | Library | Developing of the chatbot and discussing its perceived capabilities and limitations. | Pioneering application of ChatGPT-based chatbot technology in academic libraries, specifically for Zayed University Library in the United Arab Emirates. |
[74] (2023) | NutritionBot: a GPT-powered chatbot | Data retrieved using the model of ChatGPT 3.5 Legacy | Healthcare | Produce nutrition advice for users |
This study successfully integrated ChatGPT into NutritionBot, enabling the chatbot to generate pregnancy nutrition advice tailored to the patients’ lifestyles, indicating the feasibility of using language models in healthcare applications. |
[75] (2023) | ChatGPT | N/A | Healthcare | 97% of the responses were considered suitable and did not explicitly breach clinical guidelines. | The study utilized three distinct clinical scenarios, and the responses generated by ChatGPT may not be broadly applicable to other clinical contexts. |
XrayGPT [76] (2023) | GPT-4 | Healthcare | Chest Radiographs Summarization | XrayGPT scored 82% in this evaluation compared to the baseline’s 6%, further highlighting its superior performance in generating radiology-specific summaries. | Developing a conversational medical vision-language model named XrayGPT. This model is designed to analyze and answer open-ended questions about chest radiographs, bridging the gap between large vision-language models and specialized medical applications. |
[77] (2023) | ChatGPT | N/A | Hospitality | Overall enhanced hotel guest experience. | This study investigated the integration of a hotel recommender system with ChatGPT, aiming to assess how this integration affected user engagement, satisfaction, and conversion rates. |
[78] (2023) | GPT-3 | N/A | EARS | Employing ChatGPT with conventional recommender system approach. | The paper proposed an approach that advocates for a separation of responsibilities. In this approach, users safeguard their emotional profile data, while EARS service providers abstain from retaining or storing this type of data. |
Table 4.
Summary of recent ChatGPT-based studies.
Table 4.
Summary of recent ChatGPT-based studies.
Work | ChatGPT Version | Domain | Dataset | Performance |
---|---|---|---|---|
[79] | Not specified | Online shopping | Amazon beauty dataset | ChatGPT demonstrated superior performance compared to state-of-the-art methods in human evaluations for explainable recommendation tasks. This emphasizes its capability to produce explanations and summaries effectively. |
[80] | GPT-2 | Online shopping | 5-core Amazon review data | The framework achieved significant performance improvements over state-of-the-art methods by utilizing the GPT-2 language model and the BM25 search engine. It outperformed them by 75.7% and 22.2% regarding Recall@K on two publicly available datasets. |
[2] | GPT-3/3.5 | Movies | MovieLens 100K | Chat-Rec notably enhanced the outcomes in terms of top-k recommendations and exhibited superior performance in zero-shot rating prediction tasks. |
[81] | GPT-3 | Movies, books, music, and news | MovieLens-1M, Books-Amazon, CDs & Vinyl-Amazonand MIND-small datasets | The results suggested that ChatGPT achieved an ideal equilibrium between cost and performance when it is equipped with list-wise ranking capabilities. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
[ad_2]