Online negative sentiment towards Mexicans and Hispanics and impact on mental well-being: A time-series analysis of social media data during the 2016 United States presidential election

Crowdcoding, a method that outsources “coding” tasks to numerous people on the internet, has emerged as a popular approach for annotating texts and visuals. However, the performance of this approach for analyzing social media data in the context of journalism and mass communication research has not been systematically assessed. This study evaluated the validity and efficiency of crowdcoding based on the analysis of 4,000 tweets about the 2016 U.S. presidential election. The results show that compared with the traditional quantitative content analysis, crowdcoding yielded comparably valid results and was superior in efficiency, but was more expensive under most circumstances.

Download Full-text

Visual Sentiment Analysis on Social Media Data

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit2174101 ◽

2021 ◽

pp. 366-372

Author(s):

Harshala Bhoir ◽

K. Jayamalini

Keyword(s):

Social Media ◽

Sentiment Analysis ◽

State Of The Art ◽

Social Media Data ◽

Media Image ◽

The Social ◽

Textual Data ◽

Art Works ◽

Negative Sentiment ◽

Media Data

Visual sentiment analysis is the way to automatically recognize positive and negative emotions from images, videos, graphics, stickers etc. To estimate the polarity of the sentiment evoked by images in terms of positive or negative sentiment, most of the state-of-the-art works exploit the text associated to a social post provided by the user. However, such textual data is typically noisy due to the subjectivity of the user which usually includes text useful to maximize the diffusion of the social post. Proposed system will extract and employ an Objective Text description of images automatically extracted from the visual content rather than the classic Subjective Text provided by the user. The proposed System will extract three views visual view, subjective text view and objective text view of social media image and will give sentiment polarity positive, negative or neutral based on hypothesis table.

Download Full-text

Timing matters: crisis severity and occupancy rate forecasts in social unrest periods

International Journal of Contemporary Hospitality Management ◽

10.1108/ijchm-06-2020-0629 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Richard T.R. Qiu ◽

Anyu Liu ◽

Jason L. Stienmetz ◽

Yang Yu

Keyword(s):

Social Media ◽

Time Series ◽

Hospitality Industry ◽

Demand Forecasting ◽

Time Series Model ◽

Social Media Data ◽

Forecasting Accuracy ◽

Social Unrest ◽

Content Type ◽

Media Data

Purpose The impact of demand fluctuation during crisis events is crucial to the dynamic pricing and revenue management tactics of the hospitality industry. The purpose of this paper is to improve the accuracy of hotel demand forecast during periods of crisis or volatility, taking the 2019 social unrest in Hong Kong as an example. Design/methodology/approach Crisis severity, approximated by social media data, is combined with traditional time-series models, including SARIMA, ETS and STL models. Models with and without the crisis severity intervention are evaluated to determine under which conditions a crisis severity measurement improves hotel demand forecasting accuracy. Findings Crisis severity is found to be an effective tool to improve the forecasting accuracy of hotel demand during crisis. When the market is volatile, the model with the severity measurement is more effective to reduce the forecasting error. When the time of the crisis lasts long enough for the time series model to capture the change, the performance of traditional time series model is much improved. The finding of this research is that the incorporating social media data does not universally improve the forecast accuracy. Hotels should select forecasting models accordingly during crises. Originality/value The originalities of the study are as follows. First, this is the first study to forecast hotel demand during a crisis which has valuable implications for the hospitality industry. Second, this is also the first attempt to introduce a crisis severity measurement, approximated by social media coverage, into the hotel demand forecasting practice thereby extending the application of big data in the hospitality literature.

Download Full-text

Assessing Trust Versus Reliance for Technology Platforms by Systematic Literature Review

Social Media + Society ◽

10.1177/2056305120913883 ◽

2020 ◽

Vol 6 (2) ◽

pp. 205630512091388

Author(s):

Trevor Deley ◽

Elizabeth Dubois

Keyword(s):

Social Media ◽

Literature Review ◽

Presidential Election ◽

Success Rates ◽

Human Relationships ◽

Social Media Data ◽

Technology Platforms ◽

Literature Reviews ◽

Us Presidential Election ◽

Media Data

We do not trust technologies like we trust people, rather we rely on them. This article argues for an emphasis on reliance rather than trust as a concept for understanding human relationships with technology. Reliance is important because researchers can empirically measure the reliability of a given technology. We first explore two frameworks of trust and reliance. We then examine how reliance can be measured by conducting systematic literature reviews of reported success metrics for given technologies. Specifically, we examine papers which present models for predicting private traits from social media data. Of the 72 models for predicting private traits that were surveyed from 31 papers, 80% of the methods reported success rates lower than 90%, indicating a general unreliability in predicting private traits. We illustrate the current applicability of this method throughout the article by discussing the Cambridge Analytica scandal that began during the 2016 US Presidential election.

Download Full-text

Exploring Relationships between Tweet Numbers and Over-The-Counter Drug Sales for Allergic Rhinitis: Retrospective Analysis (Preprint)

10.2196/preprints.33941 ◽

2021 ◽

Author(s):

Shoko Wakamiya ◽

Osamu Morimoto ◽

Katsuhiro Omichi ◽

Hideyuki Hara ◽

Ichiro Kawase ◽

...

Keyword(s):

Social Media ◽

Time Series ◽

Allergic Rhinitis ◽

Time Series Data ◽

Series Data ◽

Sales Volume ◽

Social Media Data ◽

Drug Sales ◽

Number Of Patients ◽

Media Data

BACKGROUND Health-related social media data are increasingly being used in disease surveillance studies. In particular, surveillance of infectious diseases such as influenza has demonstrated high correlations between the number of social media posts mentioning the disease and the number of patients who went to the hospital and were diagnosed with the disease. However, the prevalence of some diseases, such as allergic rhinitis, cannot be estimated based on the number of patients alone. Specifically, patients with allergic rhinitis self-medicate by taking over-the-counter (OTC) medications without going to the hospital. Although allergic rhinitis is not a life-threatening disease, it is a major social problem because it reduces patients’ quality of life, making it essential to understand its prevalence and the motives for self-medication behavior. OBJECTIVE To help understand the prevalence of allergic rhinitis and the motives for self-care treatment using social media data, this study investigated the relationship between the number of social media posts mentioning the main symptoms of allergic rhinitis and the sales volume of OTC rhinitis medications in Japan. METHODS We collected tweets over four years from 2017 to 2020 that included keywords corresponding to the main nasal symptoms of allergic rhinitis: “sneezing,” “runny nose,” and “stuffy nose.” We also obtained the sales volume of OTC drugs, including oral medications and nasal sprays, for the same period. We then calculated the Pearson correlation coefficient between time series data on the number of tweets per week and time series data on the sales volume of OTC drugs per week. RESULTS The results showed a much higher correlation (0.8432) between the time series data on the number of tweets mentioning “stuffy nose” and the time series data on the sales volume of nasal sprays than for the other two symptoms. There was also a high correlation (0.9317) between the seasonal components of these time series data. CONCLUSIONS We investigated the relationships between social media data and behavioral patterns, such as OTC drug sales volume. Exploring these relationships would be useful as a marketing indicator to predict sales volume using social media data. In future, in-depth investigations are required to cover other diseases and countries. We investigated the relationships between social media data and behavioral patterns, such as OTC drug sales volume. Exploring these relationships would be useful as a marketing indicator to predict sales volume using social media data. In future, in-depth investigations are required to cover other diseases and countries.

Download Full-text

From FAIR data to fair data use: Methodological data fairness in health-related social media research

Big Data & Society ◽

10.1177/20539517211010310 ◽

2021 ◽

Vol 8 (1) ◽

pp. 205395172110103

Author(s):

Sabina Leonelli ◽

Rebecca Lovell ◽

Benedict W Wheeler ◽

Lora Fleming ◽

Hywel Williams

Keyword(s):

Social Media ◽

Well Being ◽

Research Process ◽

Future Research ◽

Social Media Data ◽

Data Practices ◽

Health Related Research ◽

Health Related ◽

Use Of Social Media ◽

Media Data

The paper problematises the reliability and ethics of using social media data, such as sourced from Twitter or Instagram, to carry out health-related research. As in many other domains, the opportunity to mine social media for information has been hailed as transformative for research on well-being and disease. Considerations around the fairness, responsibilities and accountabilities relating to using such data have often been set aside, on the understanding that as long as data were anonymised, no real ethical or scientific issue would arise. We first counter this perception by emphasising that the use of social media data in health research can yield problematic and unethical results. We then provide a conceptualisation of methodological data fairness that can complement data management principles such as FAIR by enhancing the actionability of social media data for future research. We highlight the forms that methodological data fairness can take at different stages of the research process and identify practical steps through which researchers can ensure that their practices and outcomes are scientifically sound as well as fair to society at large. We conclude that making research data fair as well as FAIR is inextricably linked to concerns around the adequacy of data practices. The failure to act on those concerns raises serious ethical, methodological and epistemic issues with the knowledge and evidence that are being produced.

Download Full-text

Predicting the 2020 US Presidential Election with Twitter

10.5121/csit.2021.111006 ◽

2021 ◽

Author(s):

Michael Caballero

Keyword(s):

Social Media ◽

Presidential Election ◽

Structural Data ◽

Accurate Method ◽

Special Focus ◽

Campaign Strategies ◽

Social Media Data ◽

Us Presidential Election ◽

Twitter Users ◽

Media Data

One major sub-domain in the subject of polling public opinion with social media data is electoral prediction. Electoral prediction utilizing social media data potentially would significantly affect campaign strategies, complementing traditional polling methods and providing cheaper polling in real-time. First, this paper explores past successful methods from research for analysis and prediction of the 2020 US Presidential Election using Twitter data. Then, this research proposes a new method for electoral prediction which combines sentiment, from NLP on the text of tweets, and structural data with aggregate polling, a time series analysis, and a special focus on Twitter users critical to the election. Though this method performed worse than its baseline of polling predictions, it is inconclusive whether this is an accurate method for predicting elections due to scarcity of data. More research and more data are needed to accurately measure this method’s overall effectiveness.

Download Full-text

Identifying the Real Differences of Opinion in Social Media Sentiment

International Journal of Market Research ◽

10.2501/ijmr-2013-065 ◽

2013 ◽

Vol 55 (6) ◽

pp. 757-767 ◽

Cited By ~ 2

Author(s):

Annie Pettit

Keyword(s):

Social Media ◽

Older People ◽

Word Choice ◽

Correction Factors ◽

Social Media Data ◽

Differences Of Opinion ◽

Positive Sentiment ◽

Negative Sentiment ◽

Media Sentiment ◽

Media Data

This study examined the differences in social media sentiment based on author gender, age and country. After creating ten category-generic datasets, millions of social media verbatims from thousands of websites were collected, cleaned of spam, and scored into five-point sentiment scales. The results showed that women exhibit more positive sentiment, older people exhibit more positive sentiment, and Australians exhibit more positive sentiment, while Americans share more negative sentiment. The differences were small but clear, suggesting that research methodologists should apply correction factors to ensure that their results more accurately reflect differences of opinion as opposed to differences of word choice. Business users of social media data can be reassured that correction factors are not required to improve the accuracy of their research.

Download Full-text

The Relationship Between Social Media Data and Crime Rates in the United States

Social Media + Society ◽

10.1177/2056305119834585 ◽

2019 ◽

Vol 5 (1) ◽

pp. 205630511983458

Author(s):

Yan Wang ◽

Wenchao Yu ◽

Sam Liu ◽

Sean D. Young

Keyword(s):

Public Health ◽

United States ◽

Social Media ◽

The United States ◽

Initial Study ◽

Future Research ◽

Social Media Data ◽

Crime Data ◽

Targeted Interventions ◽

Media Data

Crime monitoring tools are needed for public health and law enforcement officials to deploy appropriate resources and develop targeted interventions. Social media, such as Twitter, has been shown to be a feasible tool for monitoring and predicting public health events such as disease outbreaks. Social media might also serve as a feasible tool for crime surveillance. In this study, we collected Twitter data between May and December 2012 and crime data for the years 2012 and 2013 in the United States. We examined the association between crime data and drug-related tweets. We found that tweets from 2012 were strongly associated with county-level crime data in both 2012 and 2013. This study presents preliminary evidence that social media data can be used to help predict future crimes. We discuss how future research can build upon this initial study to further examine the feasibility and effectiveness of this approach.

Download Full-text