Exploring fine-grained sentiment values in online product reviews

Abstract

We hypothesise that it is possible to determine a fine-grained set of sentiment values over and above the simple three-way positive/neutral/negative or binary Like/Dislike distinctions by examining textual formatting features. We show that this is possible for online comments about ten different categories of products. In the context of online shopping and reviews, one of the ways to analyse consumers' feedback is by analysing comments. The rating of the "like" button on a product or a comment is not sufficient to understand the level of expression. The expression of opinion is not only identified by the meaning of the words used in the comments, nor by simply counting the number of "thumbs up", but it also includes the usage of capital letters, the use of repeated words, and the usage of emoticons. In this paper, we investigate whether it is possible to expand up to seven levels of sentiment by extracting such features. Five hundred questionnaires were collected and analysed to verify the level of "like" and "dislike" value. Our results show significant values on each of the hypotheses. For consumers, reading reviews helps them make better purchase decisions but we show there is also value to be gained in a finer-grained sentiment analysis for future commercial website platforms.

Sentiment analysis tools should take account of the number of exclamation marks!!!

“…and more than 2 exclamation marks "!!!!" of positive and negative comments has shown significant value in results in our hypothesis [26]. For the results presented below, we have exclusively focused on the variation in punctuation marks and on the number of exclamation marks in particular.…”

“…The variety of sentiment expressions were categorized based on the observation of these comments. For more details, see [26].…”

Mobile Technologies and Their Relationship to Children's Ability to Read Nonverbal Emotional Cues: A Cross-Temporal Comparison

“…Research in the field of human-computer interaction and natural language processing may lead the way; extant studies find that even text-based communication can communicate emotion through capitalization, emoticons, and repetition. [38][39][40][41] With virtual and augmented reality becoming increasingly sophisticated, the likelihood that children will learn from these technologies is high. 42 Digital media and technology are increasingly used in classrooms and at home; as such, this kind of inquiry is essential as we look to support our species in an increasingly mediated world.…”

A Method of Fine-Grained Short Text Sentiment Analysis Based on Machine Learning

“…Moraes et al [28] used TF-IDF and GI as the feature extraction algorithm respectively and then classified used Pang et al's data sets with classifiers as NB, SVM and ANN, experiments proved the ANNs were found to be superior to unbalanced data sets good expressiveness. At the same time, sentiment analysis has also begun to gradually develop from coarse to fine-grained [29][30][31]. Fink et al [32] conducted sentiment analysis using method of machine learning which subjective and objective classification using coarse-grained (sentence poles) and sentiment classification using fine-grained (clause or part-of-speech).…”