A transparent Recommendation and Interest Modeling Application

A transparent Recommendation and Interest Modeling Application (RIMA)

Project description

The goal of the transparent Recommendation and Interest Modeling Application (RIMA) is to recommend items (e.g. tweets, Twitter users, publications, researchers, conferences) and leverage explanatory visualizations to explain the recommendations (output) as well as support users in exploring, developing, and understanding their own interest models (input) in order to provide a more transparent and personalized recommendation.

These interest models are generated from users’ publications and tweets using Semantic Scholar and Twitter IDs provided by users. It applies unsupervised keyphrase extraction algorithms on the collected publications and tweets to generate keyphrase-based interests. In order to address semantic issues, Wikipedia is leveraged as a knowledge base to map the keyphrases to Wikipedia pages and generate Wikipedia-based interests.

RIMA follows a user-driven personalized explanation approach by providing explanations with different levels of detail and empowering users to steer the explanation process the way they see fit. Further, the application provides on-demand explanations, that is, the users can decide whether or not to see the explanation and they can also choose which level of explanation detail they want to see.

Project features

Publications

  • Mouadh Guesmi, Mohamed Amine Chatti, Alptug Tayyar, Qurat Ul Ain, Shoeb Joarder
    Interactive Visualizations of Transparent User Models for Self-Actualization: A Human-Centered Design Approach  Journal Article  
    In Multimodal Technologies and Interaction (MTI) journal, 2022.
      
  • Mouadh Guesmi, Mohamed Amine Chatti, Laura Vorgerd, Thao Ngo, Shoeb Joarder, Qurat Ul Ain, Arham Muslim
    Explaining User Models with Different Levels of Detail for Transparent Recommendation: A User Study   Inproceedings  Forthcoming
    In Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’22 Adjunct), Barcelona, Spain, July 2022.
  • Mohamed Amine Chatti, Mouadh Guesmi, Laura Vorgerd, Thao Ngo, Shoeb Joarder, Qurat Ul Ain, Arham Muslim
    Is More Always Better? The Effects of Personal Characteristics and Level of Detail on the Perception of Explanations in a Recommender System  Inproceedings  Forthcoming
    In Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, Barcelona, Spain, July 2022.
  • Mouadh Guesmi, Mohamed Amine Chatti, Laura Vorgerd, Shoeb Joarder, Qurat Ul Ain, Thao Ngo, Shadi Zumor, Yiqi Sun, Fangzheng Ji, Arham Muslim
    Input or Output: Effects of Explanation Focus on the Perception of Explainable Recommendation with Varying Level of Details   inproceedings
    In Proceedings of the 8th joint workshop on interfaces and Human Decision Making for Recommender Systems (IntRS '21)
      
  • Mouadh Guesmi, Mohamed Amine Chatti, Laura Vorgerd, Shoeb Joarder, Shadi Zumor, Yiqi Sun, Fangzheng Ji, Arham Muslim
    On-demand Personalized Explanation for Transparent Recommendation   Inproceedings
    In Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP '21 Adjunct).
      
  • Mohamed Amine Chatti, Fangzheng Ji, Mouadh Guesmi, Arham Muslim, Ravi Kumar Singh, and Shoeb Ahmed Joarder
    SIMT: A Semantic Interest Modeling Toolkit   Inproceedings
    In Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP '21 Adjunct) ,
      
  • Mouadh Guesmi, Mohamed Amine Chatti, Yiqi Sun, Shadi Zumor, Fangzheng Ji, Arham Muslim, Laura Vorgerd, and Shoeb Ahmed Joarder
    Open, Scrutable and Explainable Interest Models for Transparent Recommendation   Inproceedings
    In Companion Proceedings of the 26th International Conference on Intelligent User Interfaces ( IUI'21).