Identifying Situational Information during Mass Emergency

In the advent of Natural Language Processing, what finds itself in much use is analysis. This research paper finds itself in reference to the same that enables it in analysing sentiments of a text. The tasks that were covered in working with NLP includes – firstly, differentiating tweets on the basis of claims and facts, and secondly to create an effective classifier that finds out if a tweet is anti-covid vaccine, pro-covid vaccine or neutral. The beauty of our paper resides in the fact, that we have hit high end accuracies without using hefty algorithms, namely 93% for the first task using Random Forest and 45.4% for the second task using BERT’s Algorithm. Our accuracies are the best among all the teams working on the same tasks, which deepens the effect that this paper resonates. The details of the IRMiDis 2021 data challenge have been discussed elaborately here, and we hope our paper marks its significance by virtue of its own merit. © 2021 Copyright for this paper by its authors.

Sentimental Analysis of Streaming COVID-19 Twitter Data on Spark-Based Framework

Social media has become an inevitable part of human’s daily life enabling people to express their opinion, sentiments, and ideologies. During this COVID-19 pandemic when the whole world went into a lockdown situation, Twitter served as an outlet for people to express their emotions. This work proposes streaming the real-time Twitter data on COVID-19 using Twitter API and handling the streaming big data using the Apache Spark framework. Here the fake account detection to detect the non-legit accounts present in the streamed data was accomplished by the proposed feature-based algorithm which attain overall accuracy of 98.74%. This constructed fake account detection model filters out the genuine accounts from the API streamed Twitter data. Sentimental analysis on these genuine Twitter accounts is performed by modifying the Natural Language Processing (NLP) state-of-art algorithm called Bidirectional Encoder Representations from Transformers (BERT). The proposed method achieved 88.30% of classification accuracy rate by concatenation of the pooled NN layer with the influential feature. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.