Predicting opinion evolution based on information diffusion in social networks using a hybrid fuzzy based approach

Abstract

Social media plays an important role in disseminating information and analysing public and government opinions. The vast majority of previous research has examined information diffusion and opinion analysis separately. This study proposes a new framework for analysing both information diffusion and opinion evolution. The change in opinion over time is known as opinion evolution. To propose a new model for predicting information diffusion and opinion analysis in social media, a forest fire algorithm, cuckoo search, and fuzzy c-means clustering are used. The forest fire algorithm is used to determine the diffuser and non-diffuser of information in social networks, and fuzzy c-means clustering with the cuckoo search optimization algorithm is proposed to cluster Twitter content into various opinion categories and to determine opinion change. On different Twitter data sets, the proposed model outperformed the existing methods in terms of precision, recall, and accuracy.

Aspect-Based Sentimental Analysis On Social Media Data Using Deep Learning Methods

“…Divate [6] analyzed the sentiments present in the Marathi tweets using LSTM. Uthirapathy and Sandanam [7] proposed a novel method using fuzzy c means closeting for sentiment classification in tweets. Ugochi and Prasad [8] developed a classification framework for sentiment analysis.…”

“…The aspect features of sentence S are passed to the output layer for polarity classification as positive, neutral and negative. The activation function is Softmax in the output layer it takes the form as mentioned in equation (7). 𝑦(𝑎) = 𝑠𝑜𝑓𝑡𝑚𝑎𝑥 (𝑤 𝑜 𝑆 + 𝑏 0 ) (7)…”