close

Multimedia Data Mining

Student Projects in Multimedia Data Mining

Contacts (if not stated otherwise): Markus Schedl, Navid Rekabsaz

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!

 

Topics:

● Music lyrics analysis via linguistic features (LIWC, MRC, H4LvD, AFINN)
● Spatio-temporal analysis of music tweets
   ○ Comparison of music taste across regions: e.g., urban versus rural regions; region clusters with similar taste; country clusters with similar taste
   ○ Investigating the geographic spread/diffusion of music over time
● Investigating the geographic spread of music using Hawkes processes on large-scale music listening data (LFM-1b dataset)
● Does music taste correlate with culture? (comparison of music genre and Hofstede’s cultural dimensions for countries)
● Emotion recognition from multimedia data (e.g., text, audio, images)
● Predict the overall rating (and variance, i.e. agreement) of movies from audiovisual and metadata content features (MovieLens dataset)
● Predict the popularity/success (“box office revenue”) of movies from their content (audio, visual, and text features provided)
● Popularity prediction of music tracks from their content, e.g., audio and lyrics
● Predict popularity of online multimedia content (videos, images, messages, etc), e.g.,
   ○ Predicting the Popularity of Online Content , Gabor Szabo and Bernardo A. Huberman, Communications of the ACM, 53(8):80-88, August 2010.
   ○ On Popularity Prediction of Videos Shared in Online Social Networks , Haitao Li, Xiaoqiang Ma, Feng Wang Jiangchuan Liu, and Ke Xu, Proceedings of the 22nd ACM International Conference on Conference on Information and Knowledge Management (CIKM), San Francisco, CA, USA, 2013.
   ○ Twitter-driven YouTube Views: Beyond Individual Influencers , Honglin Yu, Lexing Xie, Scott Sanner, Proceedings of the 22nd ACM International Conference on Multimedia (ACM MM), Orlando, FL, USA, 2014.
   ○ The Lifecycle of a Youtube Video: Phases, Content and Popularity , Honglin Yu, Lexing Xie, Scott Sanner, Proceedings of the 9th International AAAI Conference on Weblogs and Social Media (ICWSM), Oxford, UK, 2015.
   ○ Will This Paper Increase Your h-index? Scientific Impact Prediction , Yuxiao Dong, Reid A. Johnson, and Nitesh V. Chawla, Proceedings of the Eighth ACM International Conference on Web Search and Data Mining (WSDM), Shanghai, China, 2015.
● Human context prediction from smartphone data (ExtraSensory Dataset)
● Online social network analysis (connectivity, homophily, correlation between user characteristics)
● Cross-dataset comparison of machine learning tasks in music information retrieval
● Intelligent music browsing interfaces
● Personality prediction/regression from social media/multimedia data (text, audiovisual features, preferences (for music or movies, for instance):
   ○ Azucar, Danny & Marengo, Davide & Settanni, Michele. (2018). Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis. Personality and Individual Differences. 124. 150-159.
   ○ Di Xue, Lifa Wu, Zheng Hong, Shize Guo, Liang Gao, Zhiyong Wu, Xiao-Feng Zhong, Jianshan Sun: Deep learning-based personality recognition from text posts of online social networks. Appl. Intell. 48(11): 4232-4246 (2018)
   ○ Júlio C. S. Jacques Júnior, Yagmur Güçlütürk, Marc Pérez, Umut Güçlü, Carlos Andújar, Xavier Baró, Hugo Jair Escalante, Isabelle Guyon, Marcel A. J. van Gerven, Rob van Lier, Sergio Escalera: First Impressions: A Survey on Computer Vision-Based Apparent Personality Trait Analysis. CoRR abs/1804.08046 (2018)