The recent progress of Electronic Music Distribution creates a natural pressure for fine-grained musical metadata. This metadata is needed to provide music distribution services which are able to cope with the mere size of music catalogues, and the desire of users to access music titles by similarity. In this context, we describe a project of a global music title metadatabase, and focus in the ...

Music recommendation systems can observe user’s personal preferences and suggest new tracks from a large online catalog. In the case of context-aware recommenders, user’s current emotional state plays an important role. One simple way to visualize emotions and moods is graphical emoticons. In this study, we researched a high-level mapping between genres, as descriptions of music, and emoticons,...

Previous studies have found a positive relationship between exposure to fiction and interpersonal sensitivity. However, it is unclear whether exposure to different genres of fiction may be differentially related to these outcomes for readers. The current study investigated the role of four fiction genres (i.e., Domestic Fiction, Romance, Science-Fiction/Fantasy, and Suspense/Thriller) in the re...

The genre theory has been earlier introduced as a means for analyzing organizational communication. The terms hard and soft information genre have been employed to refer to the extent and explicity of the rules that the genres are enacted by in a particular communication community. People have widely learned to use genres without explicit rules for their purpose, structure, and other features. ...

Formality is an important dimension of language style. Texts of different genres tend to have different degrees of formality. F-score (formality-score) is a most popular measure for formality to differ genres. It uses a method of combining proportions of words of different types, with nouns, adjectives, articles and prepositions as positive elements, and adverbs, verbs and interjections as nega...

This paper presents a work-in-progress on the automatic analysis of discourse genre in non-elicited speech. The study is focused on the development of bottom-up methods for automatic validation of discourse typologies found in linguistic descriptions (prosodic, syntactic, pragmatic and/or contextual and situational cues). The linguistic classification examined here opposes five discourse genres...

Emotion recognition is an open problem in Affective Computing the field. Music emotion recognition (MER) has challenges including variability of musical content across genres, the cultural background of listeners, reliability of ground truth data, and the modeling human hearing in computational domains. In this study, we focus on experimental music emotion recognition. First, we present a music...

Modern TV or radio news talk-shows include a variety of sequences which comply with specific journalistic patterns, including debates, interviews, reports. The paper deals with automatic chapter generation for TV news talk-shows, according to these different journalistic genres. It is shown that linguistic and speaker-distribution based features can lead to an efficient characterization of thes...