David Hauger

Tailoring Music Recommendations to Users by Considering Diversity, Mainstreaminess, and Novelty

A shortcoming of current approaches for music recommendation is that they consider user-specific characteristics only on a very simple level, typically as some kind of interaction between users and items when employing collaborative filtering. To alleviate this issue, we propose several user features that model aspects of the users music listening behavior: diversity, mainstreaminess, and novelty of the users music taste. To validate the proposed features, we conduct a comprehensive evaluation of a variety of music recommendation approaches (stand-alone and hybrids) on a collection of almost 200 million listening events gathered from \propername{Last.fm}. We report first results and highlight cases where our diversity, mainstreaminess, and novelty features can be beneficially integrated into music recommender systems.

Personality Correlates for Digital Concert Program Notes

In classical music concerts, the concert program notes are distributed to the audience in order to provide background information on the composer, piece and performer. So far, these have been printed documents composed mostly of text. With some delay, mobile devices are making their way also in the world of classical concerts, hence offering additional options for digital program notes comprising not only text but also images, video and audio. Furthermore, these digital program notes can be personalized. In this paper, we present the results of a user study that relates personal characteristics (personality and background musical knowledge) to preferences for digital program notes.

Mining microblogs to infer music artist similarity and cultural listening patterns

This paper aims at leveraging microblogs to address two challenges in music information retrieval (MIR), similarity estimation between music artists and inferring typical listening patterns at different granularity levels (city, country, global). From two collections of several million microblogs, which we gathered over ten months, music-related information is extracted and statistically analyzed. We propose and evaluate four co-occurrence-based methods to compute artist similarity scores. Moreover, we derive and analyze culture-specific music listening patterns to investigate the diversity of listening behavior around the world.

A model for serendipitous music retrieval

Music retrieval systems that take into account the users taste and information or entertainment need when building the results set to a query are of vital interest for academia, industry, and the passionate music listener. Unfortunately, preliminary attempts to incorporate such aspects have been rather sparse so far. Focusing on the problem of music recommendation, we therefore present a new model that combines several factors we deem to be important for personalizing retrieval results: similarity, diversity, popularity, hotness, recentness, novelty, and serendipity. We further propose different ways to measure the corresponding aspects and, where available, point to literature for a more detailed elaboration of the corresponding measures. In addition, we propose the use of social media mining techniques to address the problem of estimating popularity and hotness in a geo-aware manner.

Exploring Geospatial Music Listening Patterns in Microblog Data

Microblogs are a steadily growing, valuable, albeit noisy, source of information on interests, preferences, and activities. As music plays an important role in many human lives we aim to leverage microblogs for music listening-related information. Based on this information we present approaches to estimate artist similarity, popularity, and local trends, as well as approaches to cluster artists with respect to additional tag information. Furthermore, we elaborate a novel geo-aware interaction approach that integrates these diverse pieces of information mined from music-related tweets. Including geospatial information at the level of tweets, we also present a web-based user interface to browse the “world of music” as seen by the “Twittersphere”.

On the Influence of User Characteristics on Music Recommendation Algorithms

We investigate a range of music recommendation algorithm combinations, score aggregation functions, normalization techniques, and late fusion techniques on approximately 200 million listening events collected through Last.fm. The overall goal is to identify superior combinations for the task of artist recommendation. Hypothesizing that user characteristics influence performance on these algorithmic combinations, we consider specific user groups determined by age, gender, country, and preferred genre. Overall, we find that the performance of music recommendation algorithms highly depends on user characteristics.

From Improved Auto-Taggers to Improved Music Similarity Measures

This paper focuses on the relation between automatic tag prediction and music similarity. Intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors. We present classification experiments that verify this claim. Our results suggest a straight forward way to further improve content-based music similarity measures by improving the underlying auto-taggers.

A dataset of multimedia material about classical music: PHENICX-SMM

We present a freely available dataset of multimedia material that can be used to build enriched browsing and retrieval systems for music. It is one result of the EU-FP7 funded project “Performances as Highly Enriched aNd Interactive Concert experiences” (PHENICX) that aims at enhancing the listener experience when enjoying classical music. The presented PHENICX-SMM dataset includes in total more than 50,000 multimedia items (text, image, audio) about composers, performers, pieces, and instruments. In addition to presenting the dataset, we detail one possible use case, that of building a personalized music information system that suggests certain types and quantities of multimedia material, based on personality traits and musical experience of its users. We evaluate the system via a user study and show that people generally prefer the personalized results over non-personalized.