Aspect-Category based Sentiment Analysis with Hierarchical Graph Convolutional Network

Abstract

Most of the aspect based sentiment analysis research aims at identifying the sentiment polarities toward some explicit aspect terms while ignores implicit aspects in text. To capture both explicit and implicit aspects, we focus on aspect-category based sentiment analysis, which involves joint aspect category detection and category-oriented sentiment classification. However, currently only a few simple studies have focused on this problem. The shortcomings in the way they defined the task make their approaches difficult to effectively learn the inner-relations between categories and the inter-relations between categories and sentiments. In this work, we re-formalize the task as a category-sentiment hierarchy prediction problem, which contains a hierarchy output structure to first identify multiple aspect categories in a review sentence, and jointly predict the sentiment for each of the identified categories. Specifically, we propose a Hierarchical Graph Convolutional Network (Hier-GCN), where a lower-level GCN is to model the inner-relations among multiple categories, and the higher-level GCN is to capture the inter-relations between aspect categories and sentiments. Extensive evaluations demonstrate that our hierarchy output structure is superior over existing ones, and the Hier-GCN model consistently achieves the best results on four benchmarks.

Aspect Sentiment Quad Prediction as Paraphrase Generation

“…• Pipeline model: we cascade models in a pipeline manner for the quad prediction: HGCN (Cai et al, 2020) for jointly detecting the aspect category and sentiment polarity, followed by a BERTbased model extracting the aspect and opinion term , given the predicted aspect category and sentiment. The latter one can be either equipped with a linear layer (BERT-Linear) or a transformer block (BERT-TFM) on top.…”

“…Exploiting generation modeling for the ASQP task mainly faces two challenges: (i) how to linearize the desired sentiment information so as to facilitate the S2S learning? (ii) how can we utilize the pretrained models for tackling the task, which is a common practice now for solving various ABSA tasks Cai et al, 2020)? To handle these two challenges, we propose a novel PARA-PHRASE modeling paradigm, which transforms the ASQP task as a paraphrase generation problem (Bhagat and Hovy, 2013).…”

“…Early studies focus on the prediction of a single element such as extracting the aspect term (Liu et al, 2015;Yin et al, 2016;Xu et al, 2018;Ma et al, 2019), detecting the mentioned aspect category (Zhou et al, 2015;Bu et al, 2021), and predicting the sentiment polarity, given either an aspect term (Wang et al, 2016;Huang and Carley, 2018;Zhang and Qian, 2020) or an aspect category (Ruder et al, 2016;Hu et al, 2019a). Some works further consider the joint detection of two sentiment elements, including the pairwise extraction of aspect and opinion term (Wang et al, 2017;; the prediction of aspect term and its corresponding sentiment polarity He et al, 2019;Hu et al, 2019b;Luo et al, 2019;Chen and Qian, 2020); and the co-extraction of aspect category and sentiment polarity (Cai et al, 2020).…”

Sentiment Analysis for Social Media: A Survey

“…One of the categories of GNNs that is the GCNs have most successfully applied in realizing some NLP tasks, such as semantic role labeling, relational classification, text classification, machine translation, and especially the sentiment analysis field. Various GCNs models have been built to apply in opinions sentiment analysis on social media, including [7,11,31,38,83,85,92,98,101]. In our assessment via studying related literature, deep learning models on graphs are the most state-of-the-art approaches currently using in opinions sentiment analysis and interested by many researchers.…”

Learning rules for automatic identification of implicit aspects in Portuguese

“…The authors of [Cai et al 2020] formulated the task as a problem of hierarchical prediction of categories and sentiments, where first the algorithm identify categories of aspects in a sentence and then the sentiments related to each detected category. To do this, they used a convolutional network of hierarchical graphs (Hier-GCN).…”