One of the main interests of joining music streaming platforms is being able to discover new songs and artists to listen to. Be it through algorithmic or editorial recommendation, Deezer users discover new songs daily. However, not every person needs the same amount of discovery, people have different interests for novelty or  levels of curiosity. Moreover, this interest has many levels, some users, more specialists, are very interested in discovering music from a given genre, while others might enjoy a little bit of everything. While recommender systems literature is going towards more beyond accuracy metrics such as serendipity, novelty, and diversity, there’s no one-fits-all solution to how much novelty is relevant.

One very promising perspective for personalizing recommendation to users’ curiosity is explicitly accounting for it based on psychological findings about curiosity, arousal and conflict. The goal of this internship is to dive into the literature on the subject to define data-based actionable metrics of curiosity. 

The intern will be supervised by research scientists and engineers from the Deezer Research team, who will provide practical and scientific help with the performed task. The intern is nonetheless encouraged to propose solutions and work autonomously. For experiments, we ensure data availability (both quantitative and qualitative), cutting-edge technology and appropriate calculus power.

• Master / PhD student with a background in Computer Science / Computational Linguistics / Applied Mathematics / Statistics / Cognitive Sciences.
• Strong knowledge on applied machine learning and data mining 
• Good programming skills for data processing and experimentation (preferred python)
• Creativity and autonomy is a must!