Improvisation of Cleaning Process on Tweets for Opinion Mining

Arpita Grover, Pardeep Kumar, Kanwal Garg

OAI: oai:igi-global.com:253845 • DOI: 10.4018/IJBDAH.2020010104

In the current scenario, high accessibility to computational facilities encourage generation of a large volume of electronic data. Expansion of the data has persuaded researchers towards critical analyzation so as to extract the maximum possible patterns for wiser decisiveness. Such analysis requires curtailing of text to a better structured format by pre-processing. This scrutiny focuses on implementing pre-processing in two major steps for textual data generated by dint of Twitter API. A NoSQL, document-based database named as MongoDB is used for accumulating raw data. Thereafter, cleaning followed by data transformation is executed on accumulated tweets related to Narender Modi, Honorable Prime Minister of India.

Data Analysis & Statistics Medical, Healthcare, and Life Sciences Health Information Systems