An Adaptive Algorithm for Emotion Quotient Extraction of Viral Information Over Twitter Data

Abstract

In social media platforms, a viral information or trending term draws attention, as it asserts the impact of user content towards topic/terms. In real-time sentiment analysis, these viral terms could deliver potential insights for the analysis and decision support. A traditional sentiment analysis tool generates the level of predefined sentiments over social media content for the defined duration and lacks in the extraction of emotional impact created by the same. In these settings, it is a multifaceted task to estimate precisely the emotional quotient viral information creates. A novel algorithm is proposed, to (i) extract the sentiment and emotions quotient of current viral information over twitter, (ii) compare co-occurring trending/viral information, (iii) in-depth analysis of potential Twitter text data. The generated emotion quotients and micro-sentiment reveals several valuable insight of a viral/trending topic and assists in decision support. A use-case analysis over real-time extracted data asserts significant insights, as generated sentiments and emotional effects reveals co-relations caused by viral/trending information. The algorithm delivers an efficient, robust, and adaptable solution for the sentiment analysis also. © 2022, Springer Nature Switzerland AG.