No abstract

Abstract:In music genre classification, most approaches rely on statistical characteristics of low-level features computed on short audio frames. In these methods, it is implicitly considered that frames carry equally relevant information loads and that either individual frames, or distributions thereof, somehow capture the specificities of each genre. In this paper we study the representation space defined by shortterm audio features with respect to class boundaries, and compare different processing techniques to partition this space. These partitions are evaluated in terms of accuracy on two genre classification tasks, with several types of classifiers. Experiments show that a randomized and unsupervised partition of the space, used in conjunction with a Markov Model classifier lead to accuracies comparable to the state of the art. We also show that unsupervised partitions of the space tend to create less hubs.

Background: The present study’s main aim was to determine the predictors of movie rewatchability and recommendations. Methods: Using a sample of 318 participants, we first tested the structure of a gratification scale from watching a movie. Then, we examined the role of age, need for cognition, need for affect, extraversion, and emotional gratifications, in predicting individuals’ interest in rewatching the movie and in making recommendations. Results: As in the original proposal of the emotional gratification scale, the following dimensions were identified: fun, thrill, empathic sadness, release of emotions, social sharing, contemplative experiences, and character engagement, with acceptable model fit and reliability, convergent and divergent validity. Social sharing, contemplate experiences, need for affect and age were significant predictors of movie recommendation; whereas social sharing, thrill, extraversion, and age contributed most to explaining rewatching interest. Conclusion: This study highlights the importance of considering distinct gratifications and individual differences in predicting rewatching and movie recommendation.

No abstract

No abstract