Go to JKU Homepage
Institute of Computational Perception
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Multimedia Recommender Systems

Student Projects in Multimedia Recommender Systems

Contacts (if not stated otherwise): Markus Schedl,

These student projects can be started any time (including holidays) and can span over semester boundaries.

Remark: We are open for new proposals - if you are interested in Multimedia Recommender Systems, feel free to contact us!



● Explainability and transparency of recommendations/recommender systems
● Fairness and bias in recommender systems (data bias, algorithmic bias, debiasing, etc.)
● Investigating bias of recommender systems algorithms
● Investigating bias of recommender systems datasets
● Graph embeddings for recommendation in online social networks (Markus Schedl)
● Session-aware music recommendation (Spotify Music Streaming Sessions Dataset)
● DNN-based music recommendation from implicit feedback data (LFM-1b Dataset)
● Psychology-informed recommender systems (cognition models, affect-aware, personality-aware systems), for instance, Implementing a personality-aware recommender system, according to, e.g.:
   ○ Hsin-Chang Yang, Zi-Rui Huang: Mining personality traits from social messages for game recommender systems. Knowl.-Based Syst. 165: 157-168 (2019)
   ○ Ifeoma Adaji, Czarina Sharmaine, Simone Debrowney, Kiemute Oyibo, Julita Vassileva: Personality Based Recipe Recommendation Using Recipe Network Graphs. HCI (14) 2018: 161-170
   ○ (personality-aware MF for implicit feedback data!) Ignacio Fernández-Tobías, Matthias Braunhofer, Mehdi Elahi, Francesco Ricci, Iván Cantador: Alleviating the new user problem in collaborative filtering by exploiting personality information. User Model, opens an external URL in a new window. User-Adapt. Interact. 26(2-3): 221-255 (2016)
● Comparative study of context-aware music recommender approaches(e.g., comparison of various contextual prefiltering approaches to baseline):
   ○ Comparison of various contextual prefiltering approaches to baseline:
   ○ prefiltering on country-level, prefiltering on level urban/rural regions, prefiltering on combination of country and urban/rural level, baseline: no prefiltering (dataset of music tweets from ACMMM 2019 demo paper)
   ○ Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman, and Tony Jebara. 2018. Variational Autoencoders for Collaborative Filtering. In Proceedings of the 2018 World Wide Web Conference (WWW '18). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, 689-698. DOI, opens an external URL in a new window
   ○ M.F. Dacrema et al. Are we really making much progress? A worrying analysis of recent neural recommedation approaches, opens an external URL in a new window, RecSys'19: Proceedings of the 13th ACM Conference on Recommneder Systems, September 2019

   ○ Other state-of-the-art methods , opens an external URL in a new window
● Automatic playlist continuation (using DNNs); reimplementing approaches from:
   ○ https://arxiv.org/abs/1810.01520 ), opens an external URL in a new window
   ○ (only Master!) Qika Lin, Yaoqiang Niu, Yifan Zhu, Hao Lu, Keith Zvikomborero Mushonga, Zhendong Niu: Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations, opens an external URL in a new window. IEEE Access 6: 58990-59000 (2018)
● Investigating computational characteristics of music listening sessions and music playlists (what makes a good playlist?); based on the Million Playlist Dataset
● Investigating the perception of diversity and similarity in a set or sequence of recommendations
● Domain-specific recommender systems: music, point-of-interest, hotel/accommodation, jobs, fashion, etc.