scholarly journals Assessing Epidemic Diseases and Public Opinion through Popular Search Behavior Using Non-English Language Google Trends (Preprint)

2018 ◽  
Author(s):  
Yu-Wei Chang ◽  
Wei-Lun Chiang ◽  
Wen-Hung Wang ◽  
Chun-Yu Lin ◽  
Ling-Chien Hung ◽  
...  
Keyword(s):  
Social Media ◽  
Public Opinion ◽  
Surveillance System ◽  
English Language ◽  
Google Trends ◽  
Excellent Correlation ◽  
Epidemic Disease ◽  
Web Social ◽  
Epidemic Diseases ◽  
The Web

BACKGROUND Web social media has identified to utilize as an epidemic outbreaks surveillance tool. However, the correlation between non-English language queries search data and epidemic diseases remains unclear. OBJECTIVE This study aimed to confirm the suitable non-English language keywords research relative intensities that were sensitive and specific to estimate the level of epidemic disease and the public opinion in non-English language country. Moreover, our approach indicated that a surveillance system based on Internet activity can be served an essential tool for detecting emerging diseases with distinct symptoms (e.g. zika virus fever in Brazil, 2015), and estimating the local epidemic diseases (e.g. enterovirus infectious disease in Taiwan, 2012). Otherwise, we further evaluated whether the social media reflected social uneasiness and fear during epidemic outbreaks and natural catastrophes. Our specific aim is to develop a suitable surveillance system for monitoring epidemic outbreak and observing related public opinion in the non-English language countries. METHODS The present study was based on freely available weekly epidemic incidence data from Taiwan Center for Disease Control, and the web search query data obtained from Google Trends between October 4, 2015, and April 2, 2016. To validate whether the non-English query keywords were the excellent surveillance tools, we estimated the correlation between the web query data and epidemic incidence in Taiwan. RESULTS Based on our approach, the total of 8 influenza-related queries was introduced to the analysis. The keywords, “感冒(common cold), 發燒(fever), and 咳嗽(cough)”, revealed good to excellent correlation between the Google Trends query data and influenza incidence (r= 0.89, P< 0.001; r= 0.77, p< 0.001; r= 0.79, p< 0.001, respectively). Moreover, those also displayed a high correlation with the influenza-like illness emergency and outpatient visits. We further found the query ”腸病毒 (enteroviruses)” in Google Trends, which showed excellent correlation with enterovirus infected patients in the emergency department (r= 0.91, p< 0.001). CONCLUSIONS This result suggested that Google Trends can serve as a good surveillance tool for epidemic outbreaks even in non-English language countries. Due to online search activity indicated people’s concerns for epidemic diseases even when they do not visit hospitals, it prompted us to develop the effectiveness of epidemic monitoring in web social media, which reflected the infectious trend more timeliness than traditional reporting system. In addition, the web queries data in suitable non-English search terms can provide more advantage information for medical education, healthcare, and disease prevention.

scholarly journals Google Trends-based non-English language query data and epidemic diseases: a cross-sectional study of the popular search behaviour in Taiwan

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e034156
Author(s):  
Yu-Wei Chang ◽  
Wei-Lun Chiang ◽  
Wen-Hung Wang ◽  
Chun-Yu Lin ◽  
Ling-Chien Hung ◽  
...  
Keyword(s):  
Social Media ◽  
Cross Sectional Study ◽  
Google Trends ◽  
Sectional Study ◽  
Online Search ◽  
Excellent Correlation ◽  
Search Activity ◽  
Cross Sectional ◽  
English Speaking ◽  
Epidemic Diseases

ObjectiveThis study developed a surveillance system suitable for monitoring epidemic outbreaks and assessing public opinion in non-English-speaking countries. We evaluated whether social media reflects social uneasiness and fear during epidemic outbreaks and natural catastrophes.DesignCross-sectional study.SettingFreely available epidemic data in Taiwan.Main outcome measureWe used weekly epidemic incidence data obtained from the Taiwan Centers for Disease Control and online search query data obtained from Google Trends between 4 October 2015 and 2 April 2016. To validate whether non-English query keywords were useful surveillance tools, we estimated the correlation between online query data and epidemic incidence in Taiwan.ResultsWith our approach, we noted that keywords 感冒 (‘common cold’), 發燒 (‘fever’) and 咳嗽 (‘cough’) exhibited good to excellent correlation between Google Trends query data and influenza incidence (r=0.898, p<0.001; r=0.773, p<0.001; r=0.796, p<0.001, respectively). They also displayed high correlation with influenza-like illness emergencies (r=0.900, p<0.001; r=0.802, p<0.001; r=0.886, p<0.001, respectively) and outpatient visits (r=0.889, p<0.001; r=0.791, p<0.001; r=0.870, p<0.001, respectively). We noted that the query 腸病毒 (‘enterovirus’) exhibited excellent correlation with the number of enterovirus-infected patients in emergency departments (r=0.914, p<0.001).ConclusionsThese results suggested that Google Trends can be a good surveillance tool for epidemic outbreaks, even in Taiwan, the non-English-speaking country. Online search activity indicates that people are concerned about epidemic diseases, even if they do not visit hospitals. This prompted us to develop useful tools to monitor social media during an epidemic because such media usage reflects infectious disease trends more quickly than does traditional reporting.

Bots or journalists? News sharing on Twitter

2015 ◽  
Vol 40 (3) ◽  
Author(s):  
Anders Olof Larsson ◽  
Moe Hallvard
Keyword(s):  
Social Media ◽  
Online Communication ◽  
Online News ◽  
Highly Active ◽  
Media Services ◽  
Web Social ◽  
Online News Sites ◽  
News Sharing ◽  
Directing Attention ◽  
The Web

AbstractOnline news sites have become an internet ‘staple’, but we know little of the forces driving the popularity of such sites in relation to what could be understood as the latest iteration of the web – social media services. This research in brief article discusses empirical results regarding the uses of Twitter for news sharing. Specifically, we present a comparative analysis of links emanating from the service at hand to a series of media outlets over a six-month period in two countries; Sweden and Norway. Focusing on linking practices among highly active Twitter accounts, we problematize the assumption that online communication involves two or more humans by directing attention to more or less automated ‘bot’ accounts. In sum, it is suggested that such automated accounts need to be dealt with more explicitly by researchers as well as practitioners interested in the popularity of online news as expressed through social media activity.

scholarly journals Using Blogs: authentic material and ranking quality for SLA

2013 ◽  
Vol 21 (1) ◽  
pp. 20
Author(s):  
Xulian Coppens ◽  
Mercedes Rico ◽  
J. Enrique Agudo
Keyword(s):  
Social Media ◽  
Language Learning ◽  
Language Learners ◽  
English Language ◽  
Language Teachers ◽  
Authentic Materials ◽  
Authentic Material ◽  
The Impact ◽  
The Web

<p>Exposure real life language experiences forms an integral part of the acquisition process. Authentic materials – those derived from the culture of the target language rather than specially produced for language learners – increase the relevance of the learning experience by reusing texts taken directly from the target culture. Web 2.0 technologies increase opportunities for bringing authentic materials into formal language learning environments by allowing material to be collected, reused and shared amongst language teachers and learners. This paper aims to look at the role of blogs in facilitating the use of authentic material by English language teachers and learners and the impact of the most authoritative blogs in the wider Web and in Social Media.</p><p>To reach this objective, the blog ranking site Technorati was used to select the most popular blogs for English language learners and teachers and each blog was analysed according to the authenticity of the cultural material used for language learning. The analysis reveals that 100% of the material on 56.25% of the blogs selected was authentic material and over 70% of the material on a further 35.3% of blogs was authentic.</p><p>Secondly, the impact of these blogs in the wider Web and Social Media was measured in order to draw some conclusions regarding the role of language learning blogs outside the world of blogging and the communities they serve and provide an image of the relationship between blogs and bloggers, the Web and Social Media.</p><p>The results show an inherent bias within Web 2.0 technologies towards providing contemporary authentic material for language learning – the technology itself encourages its use – and that sometimes blogs can have an impact beyond their communities through the Web and Social Media.</p>

Online Public Opinion about COVID-19 Vaccines: A Content Analysis of Vaccine Discussions on Twitter (Preprint)

2021 ◽  
Author(s):  
Huang Huang ◽  
Yuanbo Qiu
Keyword(s):  
Social Media ◽  
Public Opinion ◽  
English Language ◽  
Early Period ◽  
Negative Attitude ◽  
Vaccine Safety ◽  
Vaccine Hesitancy ◽  
Analysis Tool ◽  
Health Providers ◽  
Vaccine Acceptance

BACKGROUND To combat the COVID-19 pandemic, various vaccines have been developed and their rollout is under way. However, the uptake rate is hindered by vaccine hesitancy influenced by the conversations on social media. It is necessary to trace public opinion toward COVID-vaccines on social media. OBJECTIVE The objective of this study is to examine the sentiments and topics of English-language twitter discussion regarding COVID-19 vaccination. Further this study also aims to explore the temporal trend of sentiments and topics over one month in the early period of vaccine roll-out. METHODS Following existing studies of vaccine acceptance and social media, we collected Tweet posts from Twitter data base using Twitter API from December 2020 to January 2021, which reflected actual public discussions toward COVID vaccination after the beginning of the rollout. After data cleansing and selection, 656,102 vaccine-related tweets were identified from 329,441 unique users. We leveraged VADER (Valence Aware Dictionary and sEntiment Reasoner) sentiment analysis tool to explore sentiment scores and Natural Language Toolkit (NLTK) to confirm relevant topics. We also depicted daily changes of sentiments and topics in COVID-vaccine-related tweets across one month period. RESULTS Forty-two percentage of tweets expressed pro-vaccine sentiments while 21% held negative attitudes. The trend of sentiment kept positive and consistent overtime, but a sudden surge of negative tweets occurred around the New Year, which was caused by some unexpected adverse incidents. The Six main topics associated with vaccines were identified: Advocation of vaccination (42,459, 6.47%), Official information releases (29,847, 4.55%), Vaccine distribution (12,946, 1.97%), Vaccine safety concerns (11,236, 1.71%), Personal vaccination experience (5,594, 0.85%) and Conspiracy theory (2,962, 0.45%). Among popular tweets that have been reposted frequently, adverse incidents reported by reliable source have triggered intense discussions about vaccine safety issues, usually in a negative attitude. CONCLUSIONS : Most tweets expressed non-negative sentiments toward vaccination. However, vaccination-related adverse incidents have triggered intense discussions in a negative attitude. Our findings can help policymakers and health providers view the whole picture of the influence of social media and develop better communicative strategies for improving vaccine acceptance.

scholarly journals A Comprehensive Study on Lexicon Based Approaches for Sentiment Analysis

2019 ◽  
Vol 8 (S2) ◽  
pp. 1-6
Author(s):  
Venkateswarlu Bonta ◽  
Nandhini Kumaresh ◽  
N. Janardhan
Keyword(s):  
Social Media ◽  
Public Opinion ◽  
Sentiment Analysis ◽  
Human Activities ◽  
Analysis Tool ◽  
Political Systems ◽  
Cornell University ◽  
Polarity Score ◽  
The Web ◽  
Comprehensive Study

In recent years, it is seen that the opinion-based postings in social media are helping to reshape business and public sentiments, and emotions have an impact on our social and political systems. Opinions are central to mostly all human activities as they are the key influencers of our behaviour. Whenever we need to make a decision, we generally want to know others opinion. Every organization and business always wants to find customer or public opinion about their products and services. Thus, it is necessary to grab and study the opinions on the Web. However, finding and monitoring sites on the web and distilling the reviews remains a big task because each site typically contains a huge volume of opinion text and the average human reader will have difficulty in identifying the polarity of each review and summarizing the opinions in them. Hence, it needs the automated sentiment analysis to find the polarity score and classify the reviews as positive or negative. This article uses NLTK, Text blob and VADER Sentiment analysis tool to classify the movie reviews which are downloaded from the website www.rottentomatoes.com that is provided by the Cornell University, and makes a comparison on these tools to find the efficient one for sentiment classification. The experimental results of this work confirm that VADER outperforms the Text blob.

scholarly journals Sentiment Analysis on Indian Indigenous Languages: A Review on Multilingual Opinion Mining

2019 ◽  
Author(s):  
Sonali Rajesh Shah ◽  
Abhishek Kaushik
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
English Language ◽  
Opinion Mining ◽  
Indigenous Languages ◽  
The Internet ◽  
Personal Experiences ◽  
Social Media Platforms ◽  
Use Of The Internet ◽  
The Web

An increase in the use of smartphones has laid to the use of the internet and social media platforms. The most commonly used social media platforms are Twitter, Facebook, WhatsApp and Instagram. People are sharing their personal experiences, reviews, feedbacks on the web. The information which is available on the web is unstructured and enormous. Hence, there is a huge scope of research on understanding the sentiment of the data available on the web. Sentiment Analysis (SA) can be carried out on the reviews, feedbacks, discussions available on the web. There has been extensive research carried out on SA in the English language, but data on the web also contains different other languages which should be analyzed. This paper aims to analyze, review and discuss the approaches, algorithms, challenges faced by the researchers while carrying out the SA on Indigenous languages.

Sign in / Sign up

Export Citation Format

Share Document