Data generated as a side effect of game play also solves computational problems and trains AI algorithms.

Since its introduction at CHI 2004, the ESP Game has inspired many similar games that share the goal of gathering data from players. This paper introduces a new mechanism for collecting labeled data using “games with a purpose. ” In this mechanism, players are provided with either the same or a different object, and asked to describe that object to each other. Based on each other’s descriptions, players must decide whether they have the same object or not. We explain why this new mechanism is superior for input data with certain characteristics, introduce an enjoyable new game called “TagATune ” that collects tags for music clips via this mechanism, and present findings on the data that is collected by this game.

Social tags are user-generated keywords associated with some resource on the Web. In the case of music, social tags have become an important component of “Web 2.0 ” recommender systems, allowing users to generate playlists based on use-dependent terms such as chill or jogging that have been applied to particular songs. In this paper, we propose a method for predicting these social tags directly from MP3 files. Using a set of 360 classifiers trained using the online ensemble learning algorithm FilterBoost, we map audio features onto social tags collected from the Web. The resulting automatic tags (or autotags) furnish information about music that is otherwise untagged or poorly tagged, allowing for insertion of previously unheard music into a social recommender. This avoids the “cold-start problem ” common in such systems. Autotags can also be used to smooth the tag space from which similarities and recommendations are made by providing a set of comparable baseline tags for all tracks in a recommender system. Because the words we learn are the same as those used by people who label their music collections, it is easy to integrate our predictions into existing similarity and prediction methods based on web data. 1

Music listeners frequently use words to describe music. Personalized music recommendation systems such as Last.fm and Pandora rely on manual annotations (tags) as a mechanism for querying and navigating large music collections. A well-known issue in such recommendation systems is known as the cold-start problem: it is not possible to recommend new songs/tracks until those songs/tracks have been manually annotated. Automatic tag annotation based on content analysis is a potential solution to this problem and has recently been gaining attention. We describe how stacked generalization can be used to improve the performance of a state-of-the-art automatic tag annotation system for music based on audio content analysis and report results on two publicly available datasets.

In this paper, we propose a competitive human computation game, KissKissBan (KKB), for image annotation. KKB is different from other human computation games since it integrates both collaborative and competitive elements in the game design. In a KKB game, one player, the blocker, competes with the other two collaborative players, the couples; while the couples try to find consensual descriptions about an image, the blocker’s mission is to prevent the couples from reaching consensus. Because of its design, KKB possesses two nice properties over the traditional human computation game. First, since the blocker is encouraged to stop the couples from reaching consensual descriptions, he will try to detect and prevent coalition between the couples; therefore, these efforts naturally form a player-level cheating-proof mechanism. Second, to evade the restrictions set by the blocker, the couples would endeavor to bring up a more diverse set of image annotations. Experiments hosted on Amazon Mechanical Turk and a gameplay survey involving 17 participants have shown that KKB is a fun and efficient game for collecting diverse image annotations.

This paper surveys the state of the art in automatic emotion recognition in music. Music is oftentimes referred to as a “language of emotion ” [1], and it is natural for us to categorize music in terms of its emotional associations. Myriad features, such as harmony, timbre, interpretation, and lyrics affect emotion, and the mood of a piece may also change over its duration. But in developing automated systems to organize music in terms of emotional content, we are faced with a problem that oftentimes lacks a welldefined answer; there may be considerable disagreement regarding the perception and interpretation of the emotions of a song or ambiguity within the piece itself. When compared to other music information retrieval tasks (e.g., genre identification), the identification of musical mood is still in its early stages, though it has received increasing attention in recent years. In this paper we explore a wide range of research in music emotion recognition, particularly focusing on methods that use contextual text information (e.g., websites, tags, and lyrics) and content-based approaches, as well as systems combining multiple feature domains. 1.

Abstract. This review article presents the state-of-the-art in contextbased music similarity estimation. It gives an overview of different sources of context-based data on music entities and summarizes various approaches for constructing similarity measures based on the collaborative or cultural knowledge that is incorporated in these data sources. The strength of such context-based measures is elaborated as well as their drawbacks discussed. 1

Microblogging services, such as Twitter, have risen enormously in popularity during the past years. Despite their popularity, such services have never been analyzed for MIR purposes, to the best of our knowledge. We hence present first investigations of the usability of music artist-related microblogging posts to perform artist labeling and similarity estimation tasks. To this end, we look into different text-based indexing models and term weighting measures. Two artist collections are used for evaluation, and the different methods are evaluated against data from last.fm. We show that microblogging posts are a valuable source for musical meta-data. 1.

We consider the problem of identifying the consensus ranking for the results of a query, given preferences among those results from a set of individual users. Once consensus rankings are identified for a set of queries, these rankings can serve for both evaluation and training of retrieval and learning systems. We present a novel approach to collecting the individual user preferences over image-search results: we use a collaborative game in which players are rewarded for agreeing on which image result is best for a query. Our approach is distinct from other labeling games because we are able to elicit directly the preferences of interest with respect to image queries extracted from query logs. As a source of relevance judgments, this data provides a useful complement to click data. Furthermore, the data is free of positional biases and is collected by the game without the risk of frustrating users with non-relevant results; this risk is prevalent in standard mechanisms for debiasing clicks. We describe data collected over 34 days from a deployed version of this game that amounts to about 18 million expressed preferences between pairs. Finally, we present several approaches to modeling this data in order to extract the consensus rankings from the preferences and better sort the search results for targeted queries.

Automatic music classification is a wide-ranging and multidisciplinary area of inquiry that offers significant benefits from both academic and commercial perspectives. This dissertation focuses on the development of jMIR, a suite of powerful, flexible, accessible and original software tools that can be used to design, share and apply a wide range of automatic music classification technologies. jMIR permits users to extract meaningful information from audio recordings, symbolic musical representations and cultural information available on the Internet; to use machine learning technologies to automatically build classification models; to automatically collect profiling statistics and detect metadata errors in musical collections; to perform experiments on large, stylistically diverse and well-labelled collections of music in both audio and symbolic formats; and to store and distribute information that is essential to automatic music classification in expressive and flexible standardised file formats. In order to have as diverse a range of applications as possible, care was taken to avoid tying jMIR to any particular types of music classification. Rather, it is designed to be a