Publication Date

Fall 2020

Advisor(s) - Committee Chair

Lukun Zheng (Director), Zhonghang Xia, Lan Nguyen and Melanie Autin

Degree Program

Department of Mathematics

Degree Type

Master of Science

Abstract

Video games have played a more and more important role in our life. While the genre classification is a deeply explored research subject by leveraging the strength of deep learning, the automatic video game genre classification has drawn little attention in academia. In this study, we compiled a large dataset of 50,000 video games, consisting of the video game covers, game descriptions and the genre information. We explored three approaches for genre classification using deep learning techniques. First, we developed five image-based models utilizing pre-trained computer vision models such as MobileNet, ResNet50 and Inception, based on the game covers. Second, we developed two text-based models, using Long-short Term Memory (LSTM) model and the Universal Sentence Encoder model, based on the game descriptions. For the third approach, we constructed a multi-modal fusion model, which concatenates extracted features from one image-based model and one text-based model. We analysed our results and revealed some challenges that exist in the task of genre classification for video games. Some future works are also proposed.

Disciplines

Artificial Intelligence and Robotics | Other Physical Sciences and Mathematics | Probability

Download

Share

COinS