Analyzing User Behavior and Sentimental in Computer Mediated Communication

Social media platforms are witnessing significant growth in both size and purpose. One specific aspect of social media platforms is sentiment analysis, by which insights into the emotions and feelings of a person can be inferred from their posted text. Twitter is a widely known social media platform in which users from different cultural and linguistic backgrounds. It is also valuable in studying a large amount of data and turning it into valuable information that can be useful in decision making. This study aims at investigating the sentiment orientation of the textual features as well as the emojis-based features of Arabic comments posted on social media, Twitter, during the World Cup 18 event. It also measures whether different results will be obtained when the text is analyzed in isolation from emojis. This paper presents the approach that involves extracting thousands of tweets, implementing the sentiment analysis, on the texts, and the emojis separately. This analysis has been conducted once via a using an artifact and once again manually, then a comparison between the results is made. This comparison shows that emojis support the sentiment orientation in the text. However, it can be relied solely neither on the text nor on emojis as they complement each other.