Collective tweet analysis for accurate user sentiment analysis - a case study with Delhi Assembly Election 2015. (2018)

• Record Type: Journal Article
• Authors: Mohan, Lija; Elayidom, M. Sudheep
• Is Part Of: International journal of big data intelligence. Volume 5:Number 4(2018)
• Page Start: 228
• Page End: 242
• Publication Date: 2018
• Subjects: twitter analysis -- collective tweet analysis -- sentiment analysis -- big data -- hadoop -- Map Reduce; Big data -- Periodicals; 005.705
• Languages: English
• ISSNs: 2053-1389

Abstract

Social media postings range from the environment and politics to technology and the entertainment industry. Since this can be construed as a form of collective wisdom, the authors decided to investigate its power at predicting the real-world outcomes. The objective was to design a keyword-aware user-based collective tweet mining approach to identify the opinion of each user, which is proved to be more accurate compared to the sentiment analysis done to each tweet. To make our application scalable, MapReduce programming on a Hadoop distributed processing framework is utilised. From the analysis done on 2015 Delhi Assembly Elections case study, we correctly predicted that Aam Admy Party has a higher support compared to the existing ruling party, BJP. Also, we compared our sentiment analysis algorithm with other existing techniques and identified that ours is efficient in terms of space and time complexity which makes it suitable for other BigData applications.