Aspect extraction for opinion mining with a deep convolutional neural network
In this presentation, we present the first deep learning approach to aspect extraction in opinion mining. Aspect extraction is a subtask of sentiment analysis that consists in identifying opinion targets in opinionated text. A deep convolutional neural network has been used to tag each word in opinionated sentences as either aspect or non-aspect word. We also developed a set of linguistic patterns for the same purpose and combined them with the neural network. The resulting ensemble classifier, coupled with a word-embedding model for sentiment analysis, allowed our approach to obtain significantly better accuracy than state-of-the-art methods.
Soujanya Poria received his BEng in Computer Science from Jadavpur University, India, in 2013. In the same year, he received the best undergraduate thesis and researcher award from Jadavpur University and was awarded Gold Plated Silver medal from the University and Tata Consultancy Service for his final year project during his undergraduate course. Soon after, Soujanya joined Nanyang Technological University as a research engineer in the School of Electrical and Electronics Engineering and, later in 2015, he joined NTU Temasek Laboratories, where he is now conducting research on aspect-based sentiment analysis in multiple domains and different modalities. In parallel with his research activities in Singapore, Soujanya is also in the process of finalizing his PhD studies in Computing Science and Mathematics at the University of Stirling, UK.