Analyzing Topic-Sentiment and Topic Evolution over Time from Social Media

2016 ◽  
pp. 97-109 ◽  
Author(s):  
Yan Hu ◽  
Xiaofei Xu ◽  
Li Li
Keyword(s):  
Social Media ◽  
Topic Evolution ◽  
Topic Sentiment ◽  
Over Time

scholarly journals Comparing News Articles and Tweets About COVID-19 in Brazil: Sentiment Analysis and Topic Modeling Approach

10.2196/24585 ◽  
2021 ◽  
Vol 7 (2) ◽  
pp. e24585
Author(s):  
Tiago de Melo ◽  
Carlos M S Figueiredo
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
News Media ◽  
Topic Modeling ◽  
Entity Recognition ◽  
Political Polarization ◽  
Important Approach ◽  
Topic Sentiment ◽  
The Impact ◽  
Over Time

Background The COVID-19 pandemic is severely affecting people worldwide. Currently, an important approach to understand this phenomenon and its impact on the lives of people consists of monitoring social networks and news on the internet. Objective The purpose of this study is to present a methodology to capture the main subjects and themes under discussion in news media and social media and to apply this methodology to analyze the impact of the COVID-19 pandemic in Brazil. Methods This work proposes a methodology based on topic modeling, namely entity recognition, and sentiment analysis of texts to compare Twitter posts and news, followed by visualization of the evolution and impact of the COVID-19 pandemic. We focused our analysis on Brazil, an important epicenter of the pandemic; therefore, we faced the challenge of addressing Brazilian Portuguese texts. Results In this work, we collected and analyzed 18,413 articles from news media and 1,597,934 tweets posted by 1,299,084 users in Brazil. The results show that the proposed methodology improved the topic sentiment analysis over time, enabling better monitoring of internet media. Additionally, with this tool, we extracted some interesting insights about the evolution of the COVID-19 pandemic in Brazil. For instance, we found that Twitter presented similar topic coverage to news media; the main entities were similar, but they differed in theme distribution and entity diversity. Moreover, some aspects represented negative sentiment toward political themes in both media, and a high incidence of mentions of a specific drug denoted high political polarization during the pandemic. Conclusions This study identified the main themes under discussion in both news and social media and how their sentiments evolved over time. It is possible to understand the major concerns of the public during the pandemic, and all the obtained information is thus useful for decision-making by authorities.

scholarly journals Framing of visual content shown on popular social media may affect viewers’ attitudes to threatened species

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Fernando Ballejo ◽  
Pablo Ignacio Plaza ◽  
Sergio Agustín Lambertucci
Keyword(s):  
Social Media ◽  
Threatened Species ◽  
Social Medium ◽  
Visual Content ◽  
Wildlife Species ◽  
Mammalian Predators ◽  
Negative Comments ◽  
Over Time ◽  
The Way

AbstractContent published on social media may affect user’s attitudes toward wildlife species. We evaluated viewers’ responses to videos published on a popular social medium, focusing particularly on how the content was framed (i.e., the way an issue is conveyed to transmit a certain meaning). We analyzed videos posted on YouTube that showed vultures interacting with livestock. The videos were negatively or positively framed, and we evaluated viewers’ opinions of these birds through the comments posted. We also analyzed negatively framed videos of mammalian predators interacting with livestock, to evaluate whether comments on this content were similar to those on vultures. We found that the framing of the information influenced the tone of the comments. Videos showing farmers talking about their livestock losses were more likely to provoke negative comments than videos not including farmer testimonies. The probability of negative comments being posted on videos about vultures was higher than for mammalian predators. Finally, negatively framed videos on vultures had more views over time than positive ones. Our results call for caution in the presentation of wildlife species online, and highlight the need for regulations to prevent the spread of misinformed videos that could magnify existing human-wildlife conflicts.

Do Materialistic Adolescents Ruminate More About Their Social Media Posts?

2020 ◽  
pp. 0044118X2098417
Author(s):  
Keeley Hynes ◽  
Daniel G. Lannin ◽  
Jeremy B. Kanter ◽  
Ani Yazedjian ◽  
Margaret M. Nauta
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Social Status ◽  
Mental Distress ◽  
External Validation ◽  
Value Orientation ◽  
Media Content ◽  
Over Time

Previous research suggests that ruminating on social media content is associated with greater mental distress (Yang et al., 2018). This study examined whether materialistic value orientation (MVO)—prioritizing values and goals related to consumerism, consumption, and social status—predicted social media rumination in a sample of diverse adolescents in a two-wave cross-lagged design. A cross-lagged analysis among 119 adolescents indicated that MVO at Wave 1 predicted greater social media rumination 4 months later at Wave 2, but social media rumination at Wave 1 did not predict MVO at Wave 2. Cross-lagged results suggested that MVO may lead to greater social media rumination over time for diverse adolescents. Adolescents with MVO could benefit from interventions to reduce the effects of their need for external validation and maladaptive rumination, as external validation and maladaptive rumination are linked to behaviors and thoughts that can be harmful to mental health.

Dynamics of convergence behaviour in social media crisis communication – a complexity perspective

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Milad Mirbabaie ◽  
Stefan Stieglitz ◽  
Felix Brünker
Keyword(s):  
Social Media ◽  
Emergency Management ◽  
Crisis Communication ◽  
Design Methodology ◽  
Content Type ◽  
The Public ◽  
Analysis Techniques ◽  
Twitter Data ◽  
Convergence Behaviour ◽  
Over Time

PurposeThe purpose of this study is to investigate communication on Twitter during two unpredicted crises (the Manchester bombings and the Munich shooting) and one natural disaster (Hurricane Harvey). The study contributes to understanding the dynamics of convergence behaviour archetypes during crises.Design/methodology/approachThe authors collected Twitter data and analysed approximately 7.5 million relevant cases. The communication was examined using social network analysis techniques and manual content analysis to identify convergence behaviour archetypes (CBAs). The dynamics and development of CBAs over time in crisis communication were also investigated.FindingsThe results revealed the dynamics of influential CBAs emerging in specific stages of a crisis situation. The authors derived a conceptual visualisation of convergence behaviour in social media crisis communication and introduced the terms hidden and visible network-layer to further understanding of the complexity of crisis communication.Research limitations/implicationsThe results emphasise the importance of well-prepared emergency management agencies and support the following recommendations: (1) continuous and (2) transparent communication during the crisis event as well as (3) informing the public about central information distributors from the start of the crisis are vital.Originality/valueThe study uncovered the dynamics of crisis-affected behaviour on social media during three cases. It provides a novel perspective that broadens our understanding of complex crisis communication on social media and contributes to existing knowledge of the complexity of crisis communication as well as convergence behaviour.

Gamifying the Media Classroom

2017 ◽  
Vol 7 (4) ◽  
pp. 22-49
Author(s):  
Katie Seaborn ◽  
Deborah I. Fels ◽  
Rob Bajko ◽  
Jaigris Hodson
Keyword(s):  
Social Media ◽  
Student Engagement ◽  
Conceptual Framework ◽  
Student Perspective ◽  
Educational Settings ◽  
The Media ◽  
Game Elements ◽  
The Impact ◽  
Over Time

Gamification, or the use of game elements in non-game contexts, has become a popular and increasingly accepted method of engaging learners in educational settings. However, there have been few comparisons of different kinds of courses and students, particularly in terms of discipline and content. Additionally, little work has reported on course instructor/designer perspectives. Finally, few studies on gamification have used a conceptual framework to assess the impact on student engagement. This paper reports on findings from evaluating two gamified multimedia and social media undergraduate courses over the course of one semester. Findings from applying a multidimensional framework suggest that the gamification approach taken was moderately effective for students overall, with some elements being more engaging than others in general and for each course over time." Post-term questionnaires posed to the instructors/course designers revealed congruence with the student perspective and several challenges pre- and post-implementation, despite the use of established rules for gamifying curricula.

scholarly journals Polarization in the contemporary political and media landscape

2020 ◽  
Author(s):  
Anne E Wilson ◽  
Victoria Parker ◽  
Matthew Feinberg
Keyword(s):  
Social Media ◽  
Political Polarization ◽  
Political Elites ◽  
Ideological Polarization ◽  
Societal Level ◽  
Polarization Phenomena ◽  
Partisan Media ◽  
Over Time

Political polarization is on the rise in America. Although social psychologists frequently study the intergroup underpinnings of polarization, they have traditionally had less to say about macro societal processes that contribute to its rise and fall. Recent cross-disciplinary work on the contemporary political and media landscape provides these complementary insights. In this paper, we consider the evidence for and implications of political polarization, distinguishing between ideological, affective, and false polarization. We review three key societal-level factors contributing to these polarization phenomena: the role of political elites, partisan media, and social media dynamics. We argue that institutional polarization processes (elites, media and social media) contribute to people’s misperceptions of division among the electorate, which in turn can contribute to a self-perpetuating cycle fueling animosity (affective polarization) and actual ideological polarization over time.

scholarly journals A trend study in the stratification of social media use among urban youth: Chile 2009-2019

2021 ◽  
Vol 1 ◽  
Author(s):  
Teresa Correa ◽  
Sebastián Valenzuela
Keyword(s):  
Social Media ◽  
Urban Youth ◽  
Urban Areas ◽  
Trend Study ◽  
Frequency Of Use ◽  
Gender And Age ◽  
Age Cohort ◽  
Youth Media ◽  
Probabilistic Survey ◽  
Over Time

This trend study describes changes and continuities in the stratification of usage of Facebook, Twitter, Instagram, and WhatsApp in Chile between 2009-2019—the decade that witnessed the rise of social media. Using the Youth, Media and Participation Study—a probabilistic survey conducted on an annual basis among 1,000 individuals aged 18 to 29 living in the three largest urban areas in Chile (N = 10,518)—we analyze how frequency of use and type of activities conducted on social media has varied over time along socioeconomic status, gender, and age cohort. Instead of a uniform trend towards less (or greater) inequality, the results show that each platform exhibits a unique dynamic. For instance, whereas SES-based inequality in frequency of use has decreased on Facebook over time, it has remained stable on WhatsApp and increased on Twitter and Instagram. In addition, significant differences in the likelihood of conducting different activities (e.g., chatting, commenting news, sharing links) remained across groups, even on platforms such as Facebook where frequency of use has equalized over time.

scholarly journals Live reality television: Care structures within the production and reception of talent shows

2018 ◽  
Vol 14 (1) ◽  
pp. 7-21
Author(s):  
Annette Hill ◽  
Tina Askanius ◽  
Koko Kondo
Keyword(s):  
Social Media ◽  
Critical Theory ◽  
Empirical Research ◽  
Reality Television ◽  
Social Experience ◽  
The Creation ◽  
Over Time

This article focuses on production and reception practices for live reality television using critical theory and empirical research to question how producers and audiences co-create and limit live experiences. The concept of care structures is used to make visible hidden labour in the creation of mood, in particular audiences as participants in the management of live experiences. In the case of Got to Dance, there was a play off between the value and meaning of the live events as a temporary experience captured by ratings and social media, and the more enduring collective-social experience of this reality series over time.

Strange Frame Fellows: The Evolution of Discursive Framing in the Opt-Out Testing Movement

2021 ◽  
Vol 123 (5) ◽  
pp. 1-32 ◽  
Author(s):  
Richard Paquin Morel
Keyword(s):  
Social Media ◽  
Public Schools ◽  
Social Issues ◽  
Qualitative Content Analysis ◽  
Research Question ◽  
The Public ◽  
Local Schools ◽  
Opt Out ◽  
Open Coding ◽  
Over Time

Background/context In recent years, opposition to accountability policies and associated testing has manifested in widespread boycotts of annual tests—mobilized as the “opt-out movement.” A central challenge facing any movement is the need to recruit and mobilize participants. Key to this process is framing—a discursive tactic in which activists present social issues as problems that require collective action to solve. Such framing often relies on compatible political and ideological commitments among activists and potential recruits. Yet the opt-out movement has successfully mobilized widespread boycotts in diverse communities. How have participants in the movement framed issues relating to testing and accountability? Purpose/objective/research question/focus of study I explore the discursive tactics of participants in the opt-out movement by analyzing how they frame issues related to testing and accountability over time. I ask two research questions: (1) What frames did participants in opt-out-aligned social media groups use to convince others that standardized accountability tests are a problem and build support for the movement? (2) To what extent and how did the deployment of frames change over time? Research design I conducted a mixed-methods study combining qualitative content analysis to identify frames and computational analysis to describe their co-deployment over time. Data collection and analysis I compiled a text corpus of posts to opt-out-aligned social media pages from 2010–2014. I analyzed posts using open coding to identify frames used by participants in online communities. Frames were categorized by their orientation—the general way in which they framed the problem of testing and accountability. I then analyzed the co-deployment of frames using network analysis and hierarchical clustering. Conclusions/recommendations The longitudinal analysis of frames reveals key differences in the frames used by participants. While more politically oriented frames—those characterizing testing as a social issue affecting the public schools at large—were common in early stages of the movement, less overtly political frames—those characterizing testing as an individual issue affecting children and local schools or a technical issue—became more prominent over time. Over time, socially oriented frames became decoupled from other frames, showing independent patterns of deployment. This suggests that the movement may have benefited from de-emphasizing politically oriented frames, but that it lacked an overarching shared narrative, which has the potential to limit how it might affect accountability policies and testing.

Tracking self-reported symptoms and medical conditions on social media during the COVID-19 pandemic (Preprint)

2021 ◽  
Author(s):  
Qinglan Ding ◽  
Daisy Massey ◽  
Chenxi Huang ◽  
Connor Grady ◽  
Yuan Lu ◽  
...  
Keyword(s):  
Mental Health ◽  
Infectious Disease ◽  
Social Media ◽  
Positive Predictive Value ◽  
Medical Condition ◽  
Medical Conditions ◽  
Health Related ◽  
The U.S ◽  
Over Time

BACKGROUND Harnessing health-related data posted on social media in real-time has the potential to offer insights into how the pandemic impacts the mental health and general well-being of individuals and populations over time. OBJECTIVE The aim of this study was to obtain information on symptoms and medical conditions self-reported by non-Twitter social media users during the coronavirus disease 2019 (COVID-19) pandemic, and to determine how discussion of these symptoms and medical conditions on social media changed over time. METHODS We used natural language processing (NLP) algorithms to identify symptom and medical condition topics being discussed on social media between June 14 and December 13, 2020. The sample social media posts were geotagged by NetBase, a third-party data provider. We calculated the positive predictive value and sensitivity to validate the classification of the posts. We also assessed the frequency of different health-related discussions on social media over time during the study period, and compared the changes in the frequency of each symptom/medical condition discussion to the fluctuation of U.S. daily new COVID-19 cases during the study period. Additionally, we compared the trends of the 5 most commonly mentioned symptoms and medical conditions from June 14 to August 31 (when the U.S. passed 6 million COVID-19 cases) to the trends observed from September 1 to December 13, 2020. RESULTS Within a total of 9,807,813 posts (nearly 70% were sourced from the U.S.), we identified discussion of 120 symptom topics and 1,542 medical condition topics. Our classification of the health-related posts had a positive predictive value of over 80% and an average classification rate of 92% sensitivity. The 5 most commonly mentioned symptoms on social media during the study period were: anxiety (in 201,303 posts or 12.2% of the total posts mentioning symptoms), generalized pain (189,673, 11.5%), weight loss (95,793, 5.8%), fatigue (91,252, 5.5%), and coughing (86,235, 5.2%). The 5 most discussed medical conditions were: COVID-19 (in 5,420,276 posts or 66.4% of the total posts mentioning medical conditions), unspecified infectious disease (469,356, 5.8%), influenza (270,166, 3.3%), unspecified disorders of the central nervous system (253,407, 3.1%), and depression (151,752, 1.9%). The changes in the frequency of 2 medical conditions, COVID-19 and unspecified infectious disease, were similar to the fluctuation of daily new confirmed cases of COVID-19 in the U.S. CONCLUSIONS COVID-19 and symptoms of anxiety were the two most commonly discussed health-related topics on social media from June 14 to December 13, 2020. Real-time monitoring of social media posts on symptoms and medical conditions may help assess the population's mental health status and enhance public health surveillance for infectious disease.

Sign in / Sign up

Export Citation Format

Share Document