Automatic Construction of an Annotated Corpus with Implicit Aspects

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 6985–6991 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 6985 Automatic Construction of an Annotated Corpus with Implicit Aspects Aye Aye Mar, Kiyoaki Shirai Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology 1-1 Asahidai, Nomi, Ishikawa, 923-1292, Japan { s1920405, kshirai }@jaist.ac.jp Abstract Aspect-based sentiment analysis (ABSA) is a task that involves classifying the polarity of aspects of the products or services described in users' reviews. Most previous work on ABSA has focused on explicit aspects, which appear as explicit words or phrases in the sentences of the review. However, users often express their opinions toward the aspects indirectly or implicitly, in which case the specific name of an aspect does not appear in the review. The current datasets used for ABSA are mainly annotated with explicit aspects. This paper proposes a novel method for constructing a corpus that is automatically annotated with implicit aspects. The main idea is that sentences containing explicit and implicit aspects share a similar context. First, labeled sentences with explicit aspects and unlabeled sentences that include implicit aspects are collected. Next, clustering is performed on these sentences so that similar sentences are merged into the same cluster. Finally, the explicit aspects are propagated to the unlabeled sentences in the same cluster, in order to construct a labeled dataset containing implicit aspects. The results of our experiments on mobile phone reviews show that our method of identifying the labels of implicit aspects achieves a maximum accuracy of 82%. Keywords: aspect-based sentiment analysis, implicit aspect, opinion mining 1. Introduction With the increase in customer reviews of products on the Web, opinion mining from those reviews has become a prominent research area. In particular, a fundamental technique for fine-grained opinion mining called aspect- based sentiment analysis (ABSA), in which sentiments are analyzed in relation to a specific aspect of a product, plays a vital role not only for customers but also for manufacturers. It allows customers to find the strong and weak points of the products in which they are interested, while manufacturers can identify the customers’ needs more accurately. In the product domain, the term “aspect” (also called “feature” in some work) means a component or attribute of the product. For example, when carrying out opinion mining from phone reviews, “battery” and “price” are examples of the aspects of a phone. In general, ABSA consists of two tasks: aspect term extraction and aspect polarity classification. The former involves extracting all aspects from the sentences in the review, while the aim of the latter is to classify whether the customer is expressing a positive, neutral, or negative opinion of each extracted aspect. Two kinds of aspects are considered in the task of aspect term extraction, namely explicit and implicit aspects. Explicit aspects are those that appear as explicit words or phrases in the review sentences, while implicit aspects are expressed implicitly, without directly mentioning …

Content truncated to 500 words