Context-sensitive and attribute-based sentiment classification of online consumer-generated content

Abstract

Purpose Vast volumes of rich online consumer-generated content (CGC) can be used effectively to gain important insights for decision-making, product improvement and brand management. Recently, many studies have proposed semi-supervised aspect-based sentiment classification of unstructured CGC. However, most of the existing CGC mining methods rely on explicitly detecting aspect-based sentiments and overlooking the context of sentiment-bearing words. Therefore, this study aims to extract implicit context-sensitive sentiment, and handle slangs, ambiguous, informal and special words used in CGC. Design/methodology/approach A novel text mining framework is proposed to detect and evaluate implicit semantic word relations and context. First, POS (part of speech) tagging is used for detecting aspect descriptions and sentiment-bearing words. Then, LDA (latent Dirichlet allocation) is used to group similar aspects together and to form an attribute. Semantically and contextually similar words are found using the skip-gram model for distributed word vectorisation. Finally, to find context-sensitive sentiment of each attribute, cosine similarity is used along with a set of positive and negative seed words. Findings Experimental results using more than 400,000 Amazon mobile phone reviews showed that the proposed method efficiently found product attributes and corresponding context-aware sentiments. This method also outperforms the classification accuracy of the baseline model and state-of-the-art techniques using context-sensitive information on data sets from two different domains. Practical implications Extracted attributes can be easily classified into consumer issues and brand merits. A brand-based comparative study is presented to demonstrate the practical significance of the proposed approach. Originality/value This paper presents a novel method for context-sensitive attribute-based sentiment analysis of CGC, which is useful for both brand and product improvement.

Asynchronous network-based model and algorithm for sentiment analysis of online public opinions

“…Many scholars applied the Word2Vec model to extract the features of words (Alshari et al. , 2017; Bansal and Srivastava, 2021; Fauzi, 2018). Zhou et al.…”

“…Machine learning techniques improve the context feature extraction (Boiy and Moens, 2009;Sebastiani, 2002). Many scholars applied the Word2Vec model to extract the features of words (Alshari et al, 2017;Bansal and Srivastava, 2021;Fauzi, 2018). Zhou et al (2019) designed a new sentiment analysis model for the sentiment analysis of Chinese Micro-blog.…”

“…, 2019). Sentiment analysis of consumers' online reviews is consequently considered as a main driver for future product sales (Bansal et al. , 2021; Hu et al.…”

“…The current issue and full text archive of this journal is available on Emerald Insight at: https://www.emerald.com/insight/0368-492X.htm effectiveness of marketing strategies (Qi et al, 2016;Wei et al, 2010;Zhong et al, 2019). Sentiment analysis of consumers' online reviews is consequently considered as a main driver for future product sales (Bansal et al, 2021;Hu et al, 2008). In recent years, some public health emergencies, such as the Ebola epidemics and the COVID-19 pandemic, have had great impacts on society.…”

Aspect context aware sentiment classification of online consumer reviews

“…Table I describes both data sets and Table II shows a few examples of consumer reviews in both data sets. As done in previous studies, we decide to label reviews with ratings above 2 as positive ( 1) and ratings below 3 as negative (0) (Table III) (Bansal and Srivastava 2018a;Bansal and Srivastava, 2019). We also use the balanced data sets in our study.…”