Student Projects in Multimedia Data Mining
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 Data Mining, feel free to contact us!
- Polarity and controversy detection in user-generated texts (Markus Schedl)
- A comparison of online social networks with respect to connectivity, homophily, and centrality characteristics of users (Markus Schedl)
- Popularity prediction of movies from their content, i.e., audio, visual, and text (Markus Schedl)
- Popularity prediction of music tracks from their content, e.g., audio and lyrics (Christine Bauer, Markus Schedl)
- Cross-dataset comparison of machine learning tasks in music information retrieval (Markus Schedl)
- Intelligent music browsing interfaces (Markus Schedl)
- Emotion detection from text (Markus Schedl, Navid Rekabsaz)
- Personality detection from text (Markus Schedl, Navid Rekabsaz)
- Music lyrics analysis via linguistic features (Markus Schedl)
- Spatio-temporal analysis of music taste (e.g., via tweets analysis): comparison across regions, geographic diffusion of music taste over time (Christine Bauer)
- Characteristics of consumers that consume mainly items that are not considered widely popular or mainstream (Christine Bauer)
- The role of appearance on a curated playlist for popularity promotion (Christine Bauer)