A multi-grained aspect vector learning model for unsupervised aspect identification

Article type: Research Article

Authors: Shi, Jinglei | Guo, Junjun | Yu, Zhengtao | Xiang, Yan^{; *}

Affiliations: Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming, China

Correspondence: [*] Corresponding author. Yan Xiang, E-mail: [email protected].

Abstract: Unsupervised aspect identification is a challenging task in aspect-based sentiment analysis. Traditional topic models are usually used for this task, but they are not appropriate for short texts such as product reviews. In this work, we propose an aspect identification model based on aspect vector reconstruction. A key of our model is that we make connections between sentence vectors and multi-grained aspect vectors using fuzzy k-means membership function. Furthermore, to make full use of different aspect representations in vector space, we reconstruct sentence vectors based on coarse-grained aspect vectors and fine-grained aspect vectors simultaneously. The resulting model can therefore learn better aspect representations. Experimental results on two datasets from different domains show that our proposed model can outperform a few baselines in terms of aspect identification and topic coherence of the extracted aspect terms.

Keywords: Aspect identification, text clustering, topic coherence, membership function, aspect extraction

DOI: 10.3233/JIFS-210175

Journal: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 6, pp. 12075-12085, 2021