A Study on Herd Behavior Using Sentiment Analysis in Online Social Network

The objective of this study was to analyze sentiments of users of online social network twitter to understand how people manifested toward the article published by the magazine Veja on 04-18-16 entitled "bela, recatada e do lar" (beautiful, demure and from home) in an attempt to understand how this behavior evolved in two weeks and to assess which events had aroused greater reaction from people. To this end, a data mining technique known as sentiment analysis was used with the help of the ETL (Extract, Transform and Load) methodology and the Naive Bayes probabilistic learning algorithm. Moreover, the null hypothesis was formulated and tested to see whether two events that took place during the collection period influenced, in fact, the polarity of analyzed sentiments in the generated database.

Download Full-text

Sentiment Analysis at Online Social Network for Cyber-Malicious Post Reviews Using Machine Learning Techniques

Studies in Computational Intelligence - Computationally Intelligent Systems and their Applications ◽

10.1007/978-981-16-0407-2_9 ◽

2021 ◽

pp. 113-130

Author(s):

Romil Rawat ◽

Vinod Mahor ◽

Sachin Chirgaiya ◽

Rabindra Nath Shaw ◽

Ankush Ghosh

Keyword(s):

Machine Learning ◽

Social Network ◽

Sentiment Analysis ◽

Online Social Network ◽

Machine Learning Techniques ◽

Learning Techniques

Download Full-text

Knowledge sharing discourse types used by key actors in online affinity spaces

Information and Learning Sciences ◽

10.1108/ils-09-2020-0211 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Priya Sharma ◽

Qiyuan Li ◽

Susan M. Land

Keyword(s):

Social Network ◽

Knowledge Sharing ◽

Sentiment Analysis ◽

Online Social Network ◽

Rule Mining ◽

Content Type ◽

Network Analyses ◽

Affinity Spaces ◽

Highly Active ◽

Affinity Space

Purpose The growth of online social network sites and their conceptualization as affinity spaces makes them well suited for exploring how individuals share knowledge and practices around specific interests or affinities. The purpose of this study is to extend what is known about highly active/key actors in online affinity spaces, especially the ways in which they sustain and contribute to knowledge sharing. Design/methodology/approach This study analyzed 514 discussion posts gathered from an online affinity space on disease management. This study used a variety of methods to answer the research questions: the authors used discourse analyses to examine the conversations in the online affinity space, social network analyses to identify the structure of participation in the space and association rule mining and sentiment analysis to identify co-occurrence of discourse codes and sentiment of the discussions. Findings The results indicate that the quality and type of discourse varies considerably between key and other actors. Key actors’ discourse in the network serves to elaborate on and explain ideas and concepts, whereas other actors provide a more supportive role and engage primarily in storytelling. Originality/value This work extends what is known about informal mentoring and the role of key actors within affinity spaces by identifying specific discourse types and types of knowledge sharing that are characteristic of key actors. Also, this study provides an example of the use of a combination of rule mining association and sentiment analysis to characterize the nature of the affinity space.

Download Full-text