Sentiment Analysis on Twitter Data: Comparative Study on Different Approaches

Abstract

Social media has become incredibly popular these days for communicating with friends and for sharing opinions. According to current statistics, almost 2.22 billion people use social media in 2016, which is roughly one third of the world population and three times of the entire population in Europe. In social media people share their likes, dislikes, opinions, interests, etc. so it is possible to know about a person’s thoughts about a specific topic from the shared data in social media. Since, twitter is one of the most popular social media in the world; it is a very good source for opinion mining and sentiment analysis about different topics. In this research, SVM with different kernel functions and Adaboost are experimented using CPD and Chi-square feature extraction techniques to explore the best sentiment classification model. The reported average accuracy of Adaboost for Chi-square and CPD are 70.2% and 66.9%. The SVM radial basis kernel and polynomial kernel with Chi-square n-grams reported average accuracy of 73.73% and 68.67% respectively. Among the performed experimentation, SVM sigmoid kernel with Chi-square n-grams provided the maximum accuracy that is 74.4%.

Sentiment Analysis Based on the BERT Model: Attitudes Towards Politicians Using Media Data

“…Within the research framework, the main issues for discussion are related to automated word processing. For most researchers, classical machine learning algorithms remain relevant [13], sometimes with certain authorial modifications of classical approaches to sentiment analysis [14; 15].…”

Data Mining for Cyberbullying and Harassment Detection in Arabic Texts

“…One aim of this research is to investigate the problem of cyberbullying in Arabic languages. As seen in previous research [1,2], there is some work done for cyberbullying in English, but none in the Arabic language. They considered the hypothesis that Arabic cyberbullying detection is a challenge.…”

“…Online social networks are attracting more people where they communicate freely with each other and can share ideas, as well as comments on various events and issues; this information is beneficial to analysis. Data mining and machine learning techniques [1,2,3] provide tools needed to analyze complex, vast, and frequently changing social media data. Applying these techniques to social media has gained new perspectives on human behavior and human interaction in recent years.…”

Digital Documentary Collections of National Cultural Heritage on the Ukrainian Regional State Archives Websites

“…Nowadays, all the regional archives (100%) have electronic means of access to funds on their websites, namely scientific reference apparatus (electronic guides/catalogs, catalogs of metric books, electronic annotating records of funds, digital copies of issue, digitized issue of funds, collections of digitized documents, digital collections of film and photo documents), while in 2016 the percentage for electronic guides was 77%, electronic describing records-82% [64,[66][67][68][69]. According to the results of monitoring research in September 2021, we have seen positive changes in development of electronic/digital archives, put that in context, all the State Archives of Ukraine (100%) have published documents in electronic format comparing to 23% in 2016 [64,68]. Archival institutions are actively pursuing the policy of accessibility and openness of archival cultural heritage to the public, providing effective information and services especially important under tightened quarantine restrictions.…”