A Framework for Topic Evolution and Tracking Their Sentiments With Time

A Framework for Topic Evolution and Tracking Their Sentiments With Time

Rahul Pradhan, Dilip Kumar Sharma
Copyright: © 2022 |Pages: 19
DOI: 10.4018/IJFSA.296589
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

With the ongoing covid-19 pandemic, people rely on online communication to remain connected as a precautionary measure to maintain social distancing. When we have no one on our side to listen and console us in state of fear and dilemma, we try to find comfort in anonymity of social media. Tracking real-time changes in sentiments are quite difficult as it could not correlate well with human understanding and emotions, which changes with time and many other factors. Collecting sentiments from users on search results, news articles, paintings, photographs are nowadays common. This is a more robust and effective method as traditional ways do not rely on a lot of retrospectives. In this paper, we will be analyzing the data collected from Twitter on Covid-19 and see topic modelling can be meant to detect sentiment analysis. The challenge is here we need to see results over time, and changes detect in topics and sentiments. We analyze our method over covid-19 data and farmer’s protest. Results from this experiment using the proposed methodology are promising and giving valuable insights.
Article Preview
Top

Introduction

The covid-19 pandemic is not only a threat to the health of the public medically but, due to lockdown and measures taken by the various government to counter the spread of this virus, had caused many psychological impacts on the general public. Covid-19 and its countermeasure compel everyone to resort for their information need to online communication. Social distancing is the prime reason teachers went online to teach, patients looking and consulting their doctors online, courts and lawyers performing proceedings online, there are many other processes involving their online versions had replaced many communications and physical contacts. Social media was flooded with messages that contain the awareness and precautionary measures to fight against coronavirus. Many a time, various people display their resentments on social media as this was the only resort they left with as no one was allowed to meet or visit any offices. Messages complaining about job losses, migration of laborers, scarcity of food, and basic enmities was quite evident on social media.

The impact of newer technologies on our economy and human behavior is needed to be studied, (Li, Liu, & Li, 2021) study the impact of rapid development in field of IoT, cloud computing, 5G and many more. They classify the researches in three categories for Large Scale Group Decision Making (LGDM): 1. Data driven decision making using LGDM, 2. Recommendation methods for LGDM and 3. Assessment Methods for Group Decision Making and Cooperative Games. In another study by (Li & Liu, 2020), they collect the researchers going on in fields of Economy, Innovation and sustainable development using Big Data and impact of intelligence decision making in these areas, they consider research such as predicting and forecast financial cycles, impact on Tourism, Chinses stock market analysis and many more that explore the usage of data driven platform for better decision making.

Another event that we took into consideration is small and might not be immensely popular outside India. The reason behind choosing this event was one we already discussed, while the other one is because of the whole debate that makes this event a hot topic on Twitter after a tweet from US pop artist and musician Rihanna (Mishra et al., 2021). In her tweet, she asked the entire world community why we are not talking (reporting or questioning or scrutinizing) about these farmers' protests. Since we discuss the reason behind our pick of this event, let us provide a background. In late 2020, the Indian government passed three agricultural reforms, which the whole farmer community did not welcome. So, farmers from the northern state of Punjab and Haryana unite themselves and troops to Delhi for protest. Since Delhi Police comes under the Union Ministry of India, these farmers stop near Delhi borders that touch with the border of Haryana. A subevent that creates much fuss and brings this whole protest to the limelight is the “2021 Farmers' Republic Day protest”. On February 26 each year, India celebrates its Republic Day, the day on which the Constitution of India came into effect throughout the Union of India. Being the capital of India, Delhi witnesses a national celebration every year in the form of a Parade. On this day in 2021, i.e., after the Parade gets over, many protestors entered the Red Fort of Delhi, a symbol of national prestige for the Union of India. One of the protestors climb a flagpole in front of Fort and try to hoist the flag of the Sikh Community (Neogi et al., 2021). This cause clash between police and farmers, which eventually let the public open its anger gate at Twitter. People associated with farmer protests need to come in defending a position on Twitter. By collecting tweets around the hashtags such as #farmerprotest, #delhiprotest, #farmerrepublicday, we try to analyses the gravity of the situation and how sentiments on this topic build and how they propagate in span to two to three weeks. Considering such events, we will know how these shorter events took Twitter on the storm for a few weeks, how they decline and build up, how they lose engagement, or whether an event shifts the trend from this event to another. For analyzing such data and making decision many systems such as (Sharma & Gupta, 2020) uses fuzzy based systems that uses entropy while another similar system (Singh & Biswas, 2020) uses rule based approach for deciding weights of features.

Complete Article List

Search this Journal:
Reset
Volume 13: 1 Issue (2024)
Volume 12: 1 Issue (2023)
Volume 11: 4 Issues (2022)
Volume 10: 4 Issues (2021)
Volume 9: 4 Issues (2020)
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing