Wehrmann, Jonatas (Pontifícia Universidade Católica do Rio Grande do Sul) | Lopes, Mauricio A. (Pontifícia Universidade Católica do Rio Grande do Sul) | Barros, Rodrigo C. (Pontifícia Universidade Católica do Rio Grande do Sul)
This paper proposes a novel neural network architecture for multi-label movie genre classification based on the textual synopsis of the movie. We design an architecture that transforms the synopsis into a $n \times d$ matrix, in which $n$ is the temporal dimension (total number of words in the synopsis, indicating the directional flow of the words) and $d$ is the word-embedding vector that densely projects the respective word onto a high-dimensional feature space. A self-attention mechanism is employed to automatically learn the importance of the features in each temporal step, so the complex mapping from synopsis to a given genre (or set of genres) can be properly performed. Experiments show that our approach outperforms state-of-the-art methods for text classification based on neural networks in the largest movie genre dataset (LMTD).
Mukta, Md. Saddam Hossain (Bangladesh University of Engineering and Technology) | Khan, Euna Mehnaz (Bangladesh University of Engineering and Technology) | Ali, Mohammed Eunus (Bangladesh University of Engineering and Technology) | Mahmud, Jalal (IBM Research)
We propose a novel technique to predict a user’s movie genre preference from her psycholinguistic attributes obtained from user social media interactions. In particular, we build machine learning based classiﬁcation models that take user tweets as input to derive her psychological attributes: personality and value scores, and gives her movie genre preference as output. We train these models using user tweets in Twitter, and her reviews and ratings of movies of different genres in Internet movie database (IMDb). We exploit a key concept of psychology, i.e., an individual’s personality and values may inﬂuence her choice in performing different actions in real life. We have investigated how personality and values independently and collectively inﬂuence a user preference on different movie genres. Our proposed model can be used for recommending movies to social media users.
We miss the movies from way back when, and some movie genres today need to step aside for a comeback! Which genres need to return to theaters? Find out in an all new CineFix Roundtable! Apple's incredible space campus is almost ready for Earth Sweden's rope skipping championship routine is a total delight
Horror is cinema's great equalizer. Whether a parable for troubled times or a scream-filled escape, film's masters of scare bring us tales that frighten us silly, explore the unspeakable and remind us that, unlike the unlucky souls onscreen, we are the ones still left alive. Though the form is often maligned, horror has never been more robust in ideas -- and popularity. With horror's highest-grossing film still in theaters, we take a look at the monster we love to fear. For American horror stories are not only having a moment, they might, in fact, turn out to be the signature genre of the present moment.