Recommender systems have become widely used in assisting users with navigating the vast amount of information available during the decision-making process. They are particularly prevalent in various web applications like YouTube, Amazon, Netflix, and Spotify. Due to their popularity, they gained much attention as a significant research topic in information retrieval. This talk aims to address critical challenging issues for improving recommender systems. (1) Firstly, we will present the methods to mitigate biased recommendations derived from popularity bias. (2) Secondly, we will explain the approaches that consider the inherent characteristics of sequential data. (3) Lastly, we will discuss the integration of recommender models with language models. Additionally, I will introduce several achievements from our lab that contribute to enhancing these issues.

I am an associate professor at the Department of Software, Sungkyunkwan University (SKKU), Korea. From Sep 2016 to Aug 2020, I was an assistant professor at SKKU, Korea. From Sep 2014~Aug 2016, I was an assistant professor at Hankuk University of Foreign Studies (HUFS), Korea. From Dec 2013 to Aug 2014, I was a postdoctoral researcher at the College of Information Sciences and Technology (IST), Pennsylvania State University, USA. In Feb 2012, I received my Ph.D. at the dept of computer science and engineering, Pohang University of Science and Technology (POSTECH), Korea. I was fortunate to work as a research intern at Microsoft Research Asia and Microsoft Research.