Abstract
User intent modeling in natural language processing deciphers user requests to allow for personalized responses. The substantial volume of research (exceeding 13,000 publications in the last decade) underscores the significance of understanding prevalent models in AI systems, with a focus on conversational recommender systems. We conducted a systematic literature review to identify models frequently employed for intent modeling in conversational recommender systems. From the collected data, we developed a decision model to assist researchers in selecting the most suitable models for their systems. Furthermore, we conducted two case studies to assess the utility of our proposed decision model in guiding research modelers in selecting user intent modeling models for developing their conversational recommender systems. Our study analyzed 59 distinct models and identified 74 commonly used features. We provided insights into potential model combinations, trends in model selection, quality concerns, evaluation measures, and frequently used datasets for training and evaluating these models. The study offers practical insights into the domain of user intent modeling, specifically enhancing the development of conversational recommender systems. The introduced decision model provides a structured framework, enabling researchers to navigate the selection of the most apt intent modeling methods for conversational recommender systems.
| Original language | English |
|---|---|
| Pages (from-to) | 1643-1706 |
| Number of pages | 64 |
| Journal | User Modeling and User-Adapted Interaction |
| Volume | 34 |
| Issue number | 5 |
| Early online date | 6 Jun 2024 |
| DOIs | |
| Publication status | Published - Nov 2024 |
Bibliographical note
Publisher Copyright:© The Author(s) 2024.
Funding
We extend our sincere gratitude to the domain experts who actively participated in and contributed to this research project. Their valuable insights and expertise have significantly enriched the quality of this study. We would like to express our appreciation to Sjaak Brinkkemper, Fabiano Dalpiaz, Gerard Wagenaar, Fernando Castor de Lima Filho, and Sergio Espana Cubillo for their invaluable feedback, which has helped us in presenting the results of this study more effectively. We are also deeply thankful to all the participants of the case studies for their cooperation and willingness to share their valuable publications, which served as essential resources in evaluating and validating the proposed decision model. Their contributions have been pivotal in ensuring the practical applicability and effectiveness of the decision model in real-world scenarios. Finally, we extend our appreciation to the journal editors and reviewers for their meticulous review of this manuscript and their constructive feedback. Their efforts have played a crucial role in enhancing the quality and clarity of this research, making it a more valuable contribution to the scientific community.
| Funders | Funder number |
|---|---|
| Sergio Espana Cubillo |
Keywords
- Conversational recommender systems
- Machine learning models
- Personalized recommendation
- Query intent
- User behavior
- User intent modeling