Abstract
Understanding “what others think” is one of the most eminent pieces of knowledge in the decision-making process required in a wide spectrum of applications. The procedure of obtaining knowledge from each aspect (property) of users' opinions is called aspect-based sentiment analysis which consists of three core sub-tasks: aspect extraction, aspect and opinion-words separation, and aspect-level polarity classification. Most successful approaches proposed in this area require a set of primary training or extensive linguistic resources, which makes them relatively costly and time consuming in different languages. To overcome the aforementioned challenges, we propose an unsupervised paradigm for aspect-based sentiment analysis, which is not only simple to use in different languages, but also holistically performs the subtasks for aspect-based sentiment analysis. Our methodology relies on three coarse-grained phases which are partitioned to manifold fine-grained operations. The first phase extracts the prior domain knowledge from dataset through selecting the preliminary polarity lexicon and aspect word sets, as representative of aspects. These two resources, as primitive knowledge, are assigned to an expectation-maximization algorithm to identify the probability of any word based on the aspect and sentiment. To determine the polarity of any aspect in the final phase, the document is firstly broken down to its constituting aspects and the probability of each aspect/polarity based on the document is calculated. To evaluate this method, two datasets in the English and Persian languages are used and the results are compared with various baselines. The experimental results show that the proposed method outperforms the baselines in terms of aspect, opinion-word extraction and aspect-level polarity classification.
Highlights
Sentiment analysis, referred to opinion mining, is the process of analyzing the characteristics of opinions, feelings and emotions expressed in textual data provided for a certain topic or object [1]
The polarity classification can be executed at three different levels: (a) Document level in which it is assumed that the whole document is about an entity and a unique polarity is determined for each document, (b) Sentence-level whereby only one aspect and polarity will be determined for each sentence of the document, and (c) Aspect-level, in which all the constituent
This paper presents a novel unsupervised aspect-based sentiment analysis method called LISA
Summary
Referred to opinion mining, is the process of analyzing the characteristics of opinions, feelings and emotions expressed in textual data provided for a certain topic or object [1]. Sentiment analysis systematically models the users’ requirements and views which in turn contributes to the organization’s perception of the customer service. The associate editor coordinating the review of this manuscript and approving it for publication was Vijay Mago. Users’ reviews in recommender systems, their interests can be extracted to offer suitable products regarding the users’ tastes [5]. One of the important subtasks in sentiment analysis is polarity classification. In this subtask, the semantic orientation of a text is distinguished through automatic analysis. The semantic orientation of a text is distinguished through automatic analysis This can be explicitly identified if the writer has a positive, negative, or neutral opinion. The polarity classification can be executed at three different levels: (a) Document level in which it is assumed that the whole document is about an entity and a unique polarity is determined for each document, (b) Sentence-level whereby only one aspect and polarity will be determined for each sentence of the document, and (c) Aspect-level, in which all the constituent
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
