Named Entity Recognition in Social Media Data

Abstract

Abstract: In recent years, a lot of research is being carried out in the field of Named Entity Recognition of Social Media data. It is now easier for anyone to convey their opinions and information without any kind of authentication, rumours have multiplied as social media is now one of the commonly used media in the entire world. The fields in which Named Entity Recognition is used for analysis of data provided from various social media sites, include rumour detection, controversy detection, sentiment analysis, medical field (such as visualisation of the spread of COVID-19 or for various kinds of dietary concerns), topic detection and event detection. The purpose here is to present a summary of the present state of social media research and the impact created by information extracted from it. Through this paper, different methods proposed for the purpose of social media data extraction using Named Entity Recognition, have been studied in detail and a comparison has been provided for the same. Most of these papers use the most common metrics for evaluation of their performance, which includes precision, recall and accuracy. The proposed models have been tested on certain datasets extracted from social media networking sites such as twitter, facebook, etc. and their evaluated performance has been compared to the models proposed by several other similar approaches.