Modified fuzzy sentiment analysis approach based on user ranking suitable for online social networks

Abstract

The rapidly increasing of sentiment analysis in social networks has lead business owners and decision makers to value opinion leaders who can influence people's impressions concerning certain business or commodity. Nevertheless, decision makers are being misled by inaccurate results due to the ignorance of perspectivism. Considering perspectivism, while computing text polarity, can help machines to reflect the human perceived sentiment within the content. This emphasises the need for integrating social behaviour (user's influence factor) with sentiment analysis (text polarity scores), providing a more pragmatic portrayal of how the writer's audience comprehend the message. In this study, a new model is proposed to intensify sentiment analysis process on Twitter. In the achievement of such, social network analysis is done using UCINET tool followed by artificial neural networks for ranking users. For sentiment classification, a hybrid approach is presented, where lexicon-based technique is combined with a fuzzy classification technique to handle language vagueness as well as for an inclusive analysis of tweets into seven classes; for the purpose of enhancing final results. The proposed model is practiced on data collected from Twitter. Results show a significant enhancement in tweets polarity scores represent more realistic sentiments.

Enhancing the Prediction of Stock Market Movement Using Neutrosophic-Logic-Based Sentiment Analysis

“…The purpose of this phase is to eliminate noise and irrelevant data from tweets to improve the effectiveness of the SA process. During this phase, several cleaning steps are performed [31]. Firstly, tweets are converted to lowercase.…”

Sentiment Level Evaluation of 3D Handicraft Products Application for Smartphones Usage

“…The authors of [21] produced machine learning models to identify people's activity in social networking by the activity providing the emotional sentiment by the proposed models, which obtained the positive rate of 87.50% and a negative rate of 95.90%. The authors of [22] generated machine learning for sentiment prediction based on people's ranking in online social media by combining behavior with social data with word polarity classes, and the proposed method obtained an accuracy of 85%.…”

“…Tracking human behavior [20][21][22] -These related works applied micro-blog datasets for developing the model for sentiment analysis. The proposed technique can conduct sentiment multi-classification based on the directed weighted ability to identify the product review with good results.…”

Prediction Algorithm of User's Brand Conversion Intention Based on Fuzzy Emotion Calculation

“…(Liu and Ling, 2019). By exploring the transformation mechanism between different types of customer value cocreation behaviors in virtual brand communities, we clarify the influencing factors between behaviors, as well as the changes in cognition, emotion and attitude of customers in the process of manifesting one behavior to another, which is conducive to the timely adjustment of relationship marketing strategies and the identification of problems in customer management, so that companies can take corresponding measures to guide, intervene and influence customers to behave in a way that is beneficial to the company (Madbouly et al, 2020;Prajogo and Purwanto, 2020;Nixon and Steuber, 2021). The active cooperation between customers and enterprises in the process of value co-creation based on virtual brand communities can, on the one hand, enable customers to obtain multiple experience values and, on the other hand, enable enterprises to maintain a high level of relationship quality with customers while satisfying their needs and gaining a sustainable competitive advantage (Putri, 2021).…”