Mesut Kaya

Aalborg University Copenhagen



Welcome! I am Mesut Kaya. You have reached my personal website. I am Postdoctoral Researcher at Aalborg University Copenhagen. You can contact me if you like.

Previously, I was a Postdoc/Research Engineer at TU Delft, Delft Data Science, Web Information Systems, Epsilon group. I have been part of mainly two different projects: (i) Fairness-AwareGroup Recommendations; (ii) Conversational Health in Social Media Platforms.

I have obtained my PhD degree from Insight Centre for Data Analytics, University College Cork, Ireland, under the supervision of Dr. Derek Bridge. During my PhD study, my research focused on the design, analysis, implementation, and experimental evaluation of diversity-aware personalized recommender algorithms. An assumption of very early work on recommender systems was that the goal of such systems was to accurately predict the users’ opinions of candidate items, and to use these predictions to select items to recommend. It was soon recognized that it is not enough for predictions to be accurate or recommendations to be merely relevant. In many domains, recommendations must not only be accurate or relevant,but they should also be novel to the user or serendipitous, and a set of recommendations must be diverse. In my PhD thesis, I focused on diversity.

I have obtained my MSc. degree from Middle East Technical University, under the supervision of Prof. Ismail Hakki Toroslu. During my MSc. study, my research was about “Sentiment Analysis of Turkish Political News”. Unlike short texts like product reviews, the problem of sentiment analysis of political columns is a more challenging task. I have analyzed the effect of using different set of features by using various supervised machine learning techniques on the task of Sentiment Analysis of Political News.

You can have a look at my recent publications from the publications page.


Sep 14, 2020 Our paper with Dr. Derek Bridge and Dr. Nava Tintarev titled Ensuring Fairness in Group Recommendations by Rank-Sensitive Balancing of Relevance has been accepted at Recsys’20 as a Long Paper.
Sep 13, 2020 Congrats to Boning Gong on his masters work accepted at the CARS 2020 Workshop at ACM RecSys: Contextual Personalized Re-Ranking of Music Recommendations through Audio Features. Joint work with Dr. Nava Tintarev.

selected publications

  1. Ensuring Fairness in Group Recommendations by Rank-Sensitive Balancing of Relevance
    Kaya, Mesut, Bridge, Derek, and Tintarev, Nava
    In Fourteenth ACM Conference on Recommender Systems 2020
  2. A Comparison of Calibrated and Intent-Aware Recommendations
    Kaya, Mesut, and Bridge, Derek
    In Proceedings of the 13th ACM Conference on Recommender Systems 2019
  3. Subprofile-Aware Diversification of Recommendations
    Kaya, Mesut, and Bridge, Derek
    User Modeling and User-Adapted Interaction 2019