Political Messaging through Language Patterns and Sentiment Analysis in Twitter Messages - Focusing on the US President Twitter

2020 ◽  
Vol 25 (3) ◽  
pp. 25-51
Author(s):  
Myunsun Kwak ◽  
Keyword(s):  
Sentiment Analysis ◽  
The Us ◽  
Language Patterns

scholarly journals The Sentiments Analysis of Donald Trump and Jokowi’s Twitters on Covid-19 Policy Dissemination

Webology ◽  
2021 ◽  
Vol 18 (1) ◽  
pp. 389-405
Author(s):  
Rahmad Agus Dwianto ◽  
Achmad Nurmandi ◽  
Salahudin Salahudin
Keyword(s):  
Data Collection ◽  
Sentiment Analysis ◽  
Computational Linguistics ◽  
Language Processing ◽  
The Us ◽  
Twitter Account ◽  
Policy Dissemination ◽  
Collection Period ◽  
Source Materials

As Covid-19 spreads to other nations and governments attempt to minimize its effect by introducing countermeasures, individuals have often used social media outlets to share their opinions on the measures themselves, the leaders implementing them, and the ways in which their lives are shifting. Sentiment analysis refers to the application in source materials of natural language processing, computational linguistics, and text analytics to identify and classify subjective opinions. The reason why this research uses a sentiment case study towards Trump and Jokowi's policies is because Jokowi and Trump have similarities in handling Covid-19. Indonesia and the US are still low in the discipline in implementing health protocols. The data collection period was chosen on September 21 - October 21 2020 because during that period, the top 5 trending on Twitter included # covid19, #jokowi, #miglobal, #trump, and #donaldtrump. So, this period is most appropriate for taking data and discussing the handling of Covid-19 by Jokowi and Trump. The result shows both Jokowi and Trump have higher negative sentiments than positive sentiments during the period. Trump had issued a controversial statement regarding the handling of Covid-19. This research is limited to the sentiment generated by the policies conveyed by the US and Indonesian Governments via @jokowi and @realDonaldTrump Twitter Account. The dataset presented in this research is being collected and analyzed using the Brand24, a software-automated sentiment analysis. Further research can increase the scope of the data and increase the timeframe for data collection and develop tools for analyzing sentiment.

Textual analysis for China’s financial markets: a review and discussion

2019 ◽  
Vol 10 (1) ◽  
pp. 1-15 ◽  
Author(s):  
Alan Huang ◽  
Wenfeng Wu ◽  
Tong Yu
Keyword(s):  
Financial Markets ◽  
Sentiment Analysis ◽  
Textual Analysis ◽  
Small Sample ◽  
Textual Information ◽  
Content Type ◽  
Survey Paper ◽  
The Past ◽  
The Us ◽  
Important Field

Purpose This is a literature survey paper. The purpose of this paper is to focus on the latest developments in textual analysis on China’s financial markets, highlighting its differences from existing works in the US markets. Design/methodology/approach The authors review the literature and carry out an experiment of sentiment analysis based on a small sample of Chinese news articles. Findings Based on the experiment of sentiment analysis, there is limited evidence on the association between sentiment and other contemporaneous or future returns. Originality/value The supply of financial textual information has grown exponentially in the past decades. Technological advancements in recent years make the programming-based analysis an effective tool to digest such information. The authors highlight the use of credible textual information and discuss directions of research in this important field.

Crossing over the Atlantic

2019 ◽  
pp. 291-304
Author(s):  
Paul Booth
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Crossing Over ◽  
Doctor Who ◽  
The Us ◽  
National Borders

This chapter explores a fan-created digital mashup, SuperWhoLock, which combines elements from the US TV series Supernatural and UK shows Doctor Who and Sherlock (the latter two being linked, at the time, by a shared showrunner, Steven Moffat). It explores SuperWhoLock’s distinctive “transfandom” as a resolutely transcultural practice especially linked to sites such as Twitter and Tumblr. This fan-created crossover “show” conveys a fantastical Anglophilia for some transcultural fans, as well as multiple differences being posited between the “official” US/UK TV texts by fans, with some of these distinctions focusing on “heritage” rather than national meanings. The chapter concludes by looking at sentiment analysis via social media, using the Crimson Hexagon analytics engine, as well as considering one specific connecting word, “vanished.” Although SuperWhoLock’s time may now have passed, it remains indicative of digital fandom’s transcultural creativity, its relationship to remix culture, and its crossing of textual and national borders.

scholarly journals Social Bots’ Sentiment Engagement in Health Emergencies: A Topic-Based Analysis of the COVID-19 Pandemic Discussions on Twitter

2020 ◽  
Vol 17 (22) ◽  
pp. 8701 ◽  
Author(s):  
Wen Shi ◽  
Diyi Liu ◽  
Jing Yang ◽  
Jing Zhang ◽  
Sanmei Wen ◽  
...  
Keyword(s):  
Public Health ◽  
Social Media ◽  
Public Opinion ◽  
Sentiment Analysis ◽  
Healthcare System ◽  
Health Risks ◽  
Emotional Support ◽  
Social Distancing ◽  
The Us ◽  
Almost All

During the COVID-19 pandemic, when individuals were confronted with social distancing, social media served as a significant platform for expressing feelings and seeking emotional support. However, a group of automated actors known as social bots have been found to coexist with human users in discussions regarding the coronavirus crisis, which may pose threats to public health. To figure out how these actors distorted public opinion and sentiment expressions in the outbreak, this study selected three critical timepoints in the development of the pandemic and conducted a topic-based sentiment analysis for bot-generated and human-generated tweets. The findings show that suspected social bots contributed to as much as 9.27% of COVID-19 discussions on Twitter. Social bots and humans shared a similar trend on sentiment polarity—positive or negative—for almost all topics. For the most negative topics, social bots were even more negative than humans. Their sentiment expressions were weaker than those of humans for most topics, except for COVID-19 in the US and the healthcare system. In most cases, social bots were more likely to actively amplify humans’ emotions, rather than to trigger humans’ amplification. In discussions of COVID-19 in the US, social bots managed to trigger bot-to-human anger transmission. Although these automated accounts expressed more sadness towards health risks, they failed to pass sadness to humans.

scholarly journals Comprehensive Analyses of Twitter for Hurricane Irma

2021 ◽  
pp. 1-21
Author(s):  
Seungil Yum
Keyword(s):  
Sentiment Analysis ◽  
Disaster Relief ◽  
The State ◽  
The South ◽  
Us States ◽  
Northeast Region ◽  
The People ◽  
The Us ◽  
Hurricane Irma

This study sheds new light on the sentiment analysis of Twitter for Hurricane Irma with respect to the US states and different periods based on comprehensive analyses. This study finds that tweets are highly related to Florida since the state is the most damaged state with respect to Hurricane Irma. This study also finds that people in other regions posted numerous tweets regarding praying for the people who are damaged by the hurricane and trying to assist in some disaster relief. Next, this study shows that the proportion of tweets is differentiated by periods and regions. In the pre-hurricane period, tweets are heavily concentrated in the South region. In the hurricane period, tweets are highly located in the Southeast and the Northeast regions. In the post-hurricane period, tweets are more posted in the Northeast region. Lastly, this study highlights that people upload numerous tweets including keywords related to regions, such as “Florida”, “Miami”, and keywords related to the hurricane, such as “safe”, “prepare”, and “evacuate”. People are also highly interested in the US president’s action to cope with the Hurricane Irma.

Sentiment Analysis of Healthcare Reviews Using Context-Based Feature Weight Embedding Technique

2021 ◽  
Vol 17 (4) ◽  
pp. 1-15
Author(s):  
*Rajalaxmi Hegde ◽  
Seema S.
Keyword(s):  
Sentiment Analysis ◽  
Recurrent Network ◽  
Machine Learning Techniques ◽  
Review Analysis ◽  
Embedding Technique ◽  
Learning Techniques ◽  
The Us ◽  
Feature Weight ◽  
Care Information ◽  
Lexical Approach

Healthcare reviews play a major role in providing feedback to consumers as well as medical care information to users. Historically, the sentiment analysis of clinical documents will help patients in analyzing the medicines and identifying the relevant medicines. Existing methods of word embeddings use only the context of words; hence, they ignore the sentiment of texts. Medical review analysis is important due to several reasons. Patients will know the results of using medicines since such information is not easily obtained from any other source. Historical results of predictive analysis say that among people aged 55-80, the death rate from 2005 to 2015 in the US was at the top for the deadliest disease, which increased exponentially. Traditional machine learning techniques use a lexical approach for feature extraction. In this paper, baseline algorithms are checked with the proposed work of the recurrent network, and results show that the method outperforms baseline methods by a significant improvement in terms of precision, recall, f-score, and accuracy.

A Perspective of Electronic Cigarette Users on the COVID-19 Pandemic in Twitter: Observational Study (Preprint)

2020 ◽  
Author(s):  
Yankun Gao ◽  
Zidian Xie ◽  
Dongmei Li
Keyword(s):  
Social Media ◽  
Immune Responses ◽  
Sentiment Analysis ◽  
Topic Modeling ◽  
Electronic Cigarette ◽  
Virus Infections ◽  
Twitter Data ◽  
The Us ◽  
Twitter Users ◽  
Negative Sentiment

BACKGROUND Previous studies indicated electronic cigarette users might be more vulnerable to COVID-19 infections and could develop more severe symptoms once contracted COVID-19 due to their impaired immune responses to virus infections. Social media has been widely used to express users’ responses to the COVID-19 pandemic. OBJECTIVE We aimed to examine the responses of electronic cigarette Twitter users to the COVID-19 pandemic using Twitter data. METHODS The COVID-19 dataset contained COVID-19-related Twitter posts (tweets) between March 5th, 2020 and April 3rd, 2020. Ecig group included Twitter users who didn’t have commercial accounts but ever retweeted e-cigarette promotion posts between May 2019 and August 2019. Twitter users who didn’t post or retweet any e-cigarette-related tweets were defined as Non-Ecig group. Sentiment analysis was conducted to compare sentiment scores towards the COVID-19 pandemic between both groups. Topic modeling was used to compare the main topics discussed between the two groups. RESULTS The US COVID-19 dataset consisted of 1,112,558 COVID-19-related tweets from 15,657 unique Twitter users in the Ecig group and 9,789,584 COVID-19-related tweets from 2,128,942 unique Twitter users in the Non-Ecig group. Sentiment analysis showed that the Ecig group have more negative sentiment scores than the Non-Ecig group. Results from topic modeling indicated the Ecig group had more concern about COVID-19 related death, while the Non-Ecig group cared more about the government’s responses to the COVID-19 pandemic. CONCLUSIONS Electronic cigarette Twitter users has more concern towards the COVID-19 pandemic. Twitter is a useful tool to timely monitor public responses to the COVID-19 pandemic.

Sign in / Sign up

Export Citation Format

Share Document