scholarly journals Predicting Twitter User Demographics using Distant Supervision from Website Traffic Data

2016 ◽  
Vol 55 ◽  
pp. 389-408 ◽  
Author(s):  
Aron Culotta ◽  
Nirmal Kumar Ravi ◽  
Jennifer Cutler
Keyword(s):  
Online Social Networks ◽  
Measurement Data ◽  
Bachelor's Degree ◽  
Political Preference ◽  
Distant Supervision ◽  
Health Marketing ◽  
The Social ◽  
Twitter Users ◽  
Audience Measurement ◽  
Textual Content

Understanding the demographics of users of online social networks has important applications for health, marketing, and public messaging. Whereas most prior approaches rely on a supervised learning approach, in which individual users are labeled with demographics for training, we instead create a distantly labeled dataset by collecting audience measurement data for 1,500 websites (e.g., 50% of visitors to gizmodo.com are estimated to have a bachelor's degree). We then fit a regression model to predict these demographics from information about the followers of each website on Twitter. Using patterns derived both from textual content and the social network of each user, our final model produces an average held-out correlation of .77 across seven different variables (age, gender, education, ethnicity, income, parental status, and political preference). We then apply this model to classify individual Twitter users by ethnicity, gender, and political preference, finding performance that is surprisingly competitive with a fully supervised approach.

A Tale of Two Cultures

2012 ◽  
Author(s):  
Gary Goertz ◽  
James Mahoney
Keyword(s):  
Social Sciences ◽  
Quantitative Research ◽  
Social Science Research ◽  
Measurement Data ◽  
Science Research ◽  
Quantitative Research Methods ◽  
Qualitative And Quantitative ◽  
The Social ◽  
Scientific Worldview ◽  
Different Cultures

Some in the social sciences argue that the same logic applies to both qualitative and quantitative research methods. This book demonstrates that these two paradigms constitute different cultures, each internally coherent yet marked by contrasting norms, practices, and toolkits. The book identifies and discusses major differences between these two traditions that touch nearly every aspect of social science research, including design, goals, causal effects and models, concepts and measurement, data analysis, and case selection. Although focused on the differences between qualitative and quantitative research, the book also seeks to promote toleration, exchange, and learning by enabling scholars to think beyond their own culture and see an alternative scientific worldview. The book is written in an easily accessible style and features a host of real-world examples to illustrate methodological points.

scholarly journals Using a Quasi-Experimental Study to Examine Outcomes for Older Adult Intergenerational Program Participants

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 543-543
Author(s):  
Skye Leedahl ◽  
Melanie Brasher ◽  
Erica Estus
Keyword(s):  
Experimental Study ◽  
Rhode Island ◽  
Older Adult ◽  
Online Social Networks ◽  
Intergenerational Learning ◽  
Senior Center ◽  
Public Authorities ◽  
The Social ◽  
Quasi Experimental ◽  
The University

Abstract To more rigorously examine the University of Rhode Island Cyber-Seniors Program, we conducted a quasi-experimental study to examine if older adult senior center participants (n=25) improved scores on social and technological measures compared to a sample of senior center participants (n=25) who did not take part in the program. Findings showed that participants improved on technology measures compared to the non-participants, including searching and finding information about goods & services, obtaining information from public authorities or services, seeking health information, sending or receiving emails, and participating in online social networks (p<.05). However, participants did not change on social measures. There is either a need to identify better social measures to understand the social benefits of taking part, or to bolster the program to aid in helping older adults alleviate isolation and loneliness. Information on best practices and challenges for gathering outcomes from older participants will be discussed. Part of a symposium sponsored by Intergenerational Learning, Research, and Community Engagement Interest Group.

scholarly journals Steganographic visual story with mutual-perceived joint attention

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Yanyang Guo ◽  
Hanzhou Wu ◽  
Xinpeng Zhang
Keyword(s):  
Social Support ◽  
Social Media ◽  
Deep Learning ◽  
Joint Attention ◽  
Online Social Networks ◽  
Generation Model ◽  
High Quality ◽  
Visual Storytelling ◽  
The Social ◽  
User Intervention

AbstractSocial media plays an increasingly important role in providing information and social support to users. Due to the easy dissemination of content, as well as difficulty to track on the social network, we are motivated to study the way of concealing sensitive messages in this channel with high confidentiality. In this paper, we design a steganographic visual stories generation model that enables users to automatically post stego status on social media without any direct user intervention and use the mutual-perceived joint attention (MPJA) to maintain the imperceptibility of stego text. We demonstrate our approach on the visual storytelling (VIST) dataset and show that it yields high-quality steganographic texts. Since the proposed work realizes steganography by auto-generating visual story using deep learning, it enables us to move steganography to the real-world online social networks with intelligent steganographic bots.

scholarly journals Linguistic drivers of misinformation diffusion on social media during the COVID-19 pandemic

2021 ◽  
Author(s):  
Giandomenico Di Domenico ◽  
Annamaria Tuan ◽  
Marco Visentin
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
New Technologies ◽  
Fake News ◽  
Conspiracy Theories ◽  
Social Media Platform ◽  
The Social ◽  
Media Platform ◽  
Textual Cues ◽  
Twitter Users

AbstractIn the wake of the COVID-19 pandemic, unprecedent amounts of fake news and hoax spread on social media. In particular, conspiracy theories argued on the effect of specific new technologies like 5G and misinformation tarnished the reputation of brands like Huawei. Language plays a crucial role in understanding the motivational determinants of social media users in sharing misinformation, as people extract meaning from information based on their discursive resources and their skillset. In this paper, we analyze textual and non-textual cues from a panel of 4923 tweets containing the hashtags #5G and #Huawei during the first week of May 2020, when several countries were still adopting lockdown measures, to determine whether or not a tweet is retweeted and, if so, how much it is retweeted. Overall, through traditional logistic regression and machine learning, we found different effects of the textual and non-textual cues on the retweeting of a tweet and on its ability to accumulate retweets. In particular, the presence of misinformation plays an interesting role in spreading the tweet on the network. More importantly, the relative influence of the cues suggests that Twitter users actually read a tweet but not necessarily they understand or critically evaluate it before deciding to share it on the social media platform.

scholarly journals An Exploratory Study of COVID-19 Information on Twitter in the Greater Region

2021 ◽  
Vol 5 (1) ◽  
pp. 5
Author(s):  
Ninghan Chen ◽  
Zhiqiang Zhong ◽  
Jun Pang
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Online Social Networks ◽  
Exploratory Study ◽  
Representation Learning ◽  
Data Driven ◽  
Learning Methods ◽  
Twitter Users ◽  
Over Time

The outbreak of the COVID-19 led to a burst of information in major online social networks (OSNs). Facing this constantly changing situation, OSNs have become an essential platform for people expressing opinions and seeking up-to-the-minute information. Thus, discussions on OSNs may become a reflection of reality. This paper aims to figure out how Twitter users in the Greater Region (GR) and related countries react differently over time through conducting a data-driven exploratory study of COVID-19 information using machine learning and representation learning methods. We find that tweet volume and COVID-19 cases in GR and related countries are correlated, but this correlation only exists in a particular period of the pandemic. Moreover, we plot the changing of topics in each country and region from 22 January 2020 to 5 June 2020, figuring out the main differences between GR and related countries.

Understanding Online Conversation about COVID-19 Vaccine on Twitter: Data Mining Approach (Preprint)

2021 ◽  
Author(s):  
Ekaterina Malova
Keyword(s):  
Online Social Networks ◽  
Information Seeking ◽  
Information Dissemination ◽  
Vaccine Development ◽  
Online Communication ◽  
Vaccine Safety ◽  
Interaction Patterns ◽  
Twitter Users ◽  
The Government ◽  
Online Conversation

BACKGROUND Timely vaccination against COVID-19 can prevent a large number of people from getting infected. However, given the disease novelty and fast vaccine development, some people are hesitant to vaccinate. Online social networks like Twitter produce huge amounts of public health information and impact peoples' vaccination decisions. Hence, it is important to understand the conversation around the COVID-19 vaccination through the lens of social media. OBJECTIVE The present study aimed to define the nature of a larger Twitter conversation around the COVID-19 vaccine and explored interaction patterns between Twitter users engaged in such a conversation. METHODS Data collection took place in November 2020 on the wave of the news about the COVID-19 vaccine breakthrough. In total, 9600 Twitter posts were analyzed using a combination of text and network analysis. RESULTS Results of this study show that mixed-emotions reactions and discussions about potential side effects and vaccine safety dominated the online conversation. Twitter was primarily used for two purposes: information dissemination and opinion expression. Overall, the communication network was sparse, non-reciprocal, decentralized, and highly modular. Four main network clusters highlighted different groups of conversation stakeholders. CONCLUSIONS This study provides important insights into public sentiments, information-seeking behaviors, and online communication patterns during a major COVID-19 crisis. Given the popularity of Twitter among different types of communities and its power for rapid information dissemination, it can be an effective tool for vaccination promotion. Thus, it should be actively used to promote safe and effective vaccination through major stakeholders in the government, science, and health sectors.

scholarly journals As Representações Sociais da Dança: um Mergulho no Universo dos Estudantes de Bacharelado em Educação Física

2021 ◽  
Vol 22 (2) ◽  
pp. 231-235
Author(s):  
Felipe da Silva Triani ◽  
Glhevysson dos Santos Barros
Keyword(s):  
Social Representations ◽  
Free Association ◽  
Well Being ◽  
Bachelor's Degree ◽  
Social Representation ◽  
The Body ◽  
Rhythmic Movements ◽  
Technical Procedure ◽  
The Social ◽  
Health And Well Being

ResumoA dança é a arte de movimentar expressivamente o corpo seguindo movimentos ritmados, em geral ao som de música. Dessa forma, o significado da dança vai além da expressão artística, podendo ser vista como um meio para adquirir conhecimentos ou como opção de lazer. No campo de atuação do bacharelado, as investigações acadêmicas ainda são tímidas, urgindo de produções científicas que possam alimentar o campo científico sobre o tema. Dessa forma, o objetivo do estudo foi identificar e analisar as representações sociais que um grupo de bacharelandos do curso em Educação Física compartilha sobre a dança. A metodologia da pesquisa envolve uma abordagem qualitativa, tendo o estudo de campo como procedimento técnico. A amostra foi constituída por 200 indivíduos, sendo 85 homens e 115 mulheres com médias de idade entre 17 a 45 anos. A coleta de dados ocorreu através de questionário com associação livre de palavras, cujo termo indutor foi ”dança”. A análise foi feita por meio dos conteúdos das respostas. O resultado principal do estudo apontou que a maioria dos estudantes emprega sentido de dança como uma atividade técnica e a associam com saúde mental e bem-estar. Palavras-chave: Representação Social. Educação Física. Dança. AbstractDance is the art of expressively moving the body following rhythmic movements, usually to the sound of music. Thus, the meaning of dance goes beyond artistic expression, and can be seen as a means to acquire knowledge or as a leisure option. In the field of performance of the bachelor's degree, academic investigations are still timid, urging scientific productions that can feed the scientific field on the theme. Thus, the objective of the study was to identify and analyze the social representations that a group of Physical Education course bachelors shares about dance. The research methodology is a qualitative approach, with the field study as a technical procedure. The sample consisted of 200 individuals, 85 men and 115 women with a mean age between 17 and 45 years. Data collection was carried out through a questionnaire with free association of words, whose inducing term was, "dance". The analysis was done through the responses content. The main result of the study pointed out that most students use dance as a technical activity and associate it with mental health and well-being. Keywords: Social Representation. PE. Dance.

scholarly journals The social class gap in bachelor’s and master’s completion: university dropout in times of educational expansion

2021 ◽  
Author(s):  
Jens-Peter Thomsen
Keyword(s):  
Higher Education ◽  
Social Class ◽  
Bachelor's Degree ◽  
Disadvantaged Students ◽  
Educational Expansion ◽  
Master's Level ◽  
Percentage Points ◽  
The Social ◽  
Upper Secondary ◽  
University Dropout

While many papers have focused on socially unequal admissions in higher education, this paper looks at the persistence of class differentials after enrolment. I examine the social class gap in bachelor’s programme dropout and in the transition from bachelor’s to master’s in Denmark from the formal introduction of the bachelor’s degree in 1993 up to recent cohorts. Using administrative data, I find that the class gap in bachelor’s departures has remained constant from 1993 to 2006, with disadvantaged students being around 15 percentage points more likely to leave a bachelor’s programme than advantaged students, even after adjusting for other factors such as grades from upper secondary school. Importantly, the class gap reappears at the master’s level, with privileged students being more likely to pursue a master’s degree than less privileged students. The size of the class gap is remarkable, given that this gap is found among a selected group of university enrolees. As other studies have found that educational expansion in higher education is not necessarily a remedy for narrowing the class gap in educational attainment, scholars need to pay more attention to keeping disadvantaged students from leaving higher education.

scholarly journals Online social networks as formal learning environments: Learner experiences and activities

2012 ◽  
Vol 13 (1) ◽  
pp. 144 ◽  
Author(s):  
George Veletsianos ◽  
Cesar Navarrete
Keyword(s):  
Social Network ◽  
Social Networking ◽  
Online Social Networks ◽  
Social Networking Sites ◽  
Learning Experience ◽  
Online Social Network ◽  
Online Course ◽  
Formal Learning ◽  
The Social

<p>While the potential of social networking sites to contribute to educational endeavors is highlighted by researchers and practitioners alike, empirical evidence on the use of such sites for formal online learning is scant. To fill this gap in the literature, we present a case study of learners’ perspectives and experiences in an online course taught using the Elgg online social network. Findings from this study indicate that learners enjoyed and appreciated both the social learning experience afforded by the online social network and supported one another in their learning, enhancing their own and other students’ experiences. Conversely, results also indicate that students limited their participation to course-related and graded activities, exhibiting little use of social networking and sharing. Additionally, learners needed support in managing the expanded amount of information available to them and devised strategies and “workarounds” to manage their time and participation.<br /><strong></strong></p>

On the Aggression Diffusion Modeling and Minimization in Twitter

2022 ◽  
Vol 16 (1) ◽  
pp. 1-24
Author(s):  
Marinos Poiitis ◽  
Athena Vakali ◽  
Nicolas Kourtellis
Keyword(s):  
Online Social Networks ◽  
Important Research ◽  
Diffusion Modeling ◽  
Propagation Modeling ◽  
Twitter Data ◽  
Edge Weighting ◽  
Linear Threshold ◽  
Important Research Topic ◽  
The Social ◽  
Independent Cascade

Aggression in online social networks has been studied mostly from the perspective of machine learning, which detects such behavior in a static context. However, the way aggression diffuses in the network has received little attention as it embeds modeling challenges. In fact, modeling how aggression propagates from one user to another is an important research topic, since it can enable effective aggression monitoring, especially in media platforms, which up to now apply simplistic user blocking techniques. In this article, we address aggression propagation modeling and minimization in Twitter, since it is a popular microblogging platform at which aggression had several onsets. We propose various methods building on two well-known diffusion models, Independent Cascade ( IC ) and Linear Threshold ( LT ), to study the aggression evolution in the social network. We experimentally investigate how well each method can model aggression propagation using real Twitter data, while varying parameters, such as seed users selection, graph edge weighting, users’ activation timing, and so on. It is found that the best performing strategies are the ones to select seed users with a degree-based approach, weigh user edges based on their social circles’ overlaps, and activate users according to their aggression levels. We further employ the best performing models to predict which ordinary real users could become aggressive (and vice versa) in the future, and achieve up to AUC = 0.89 in this prediction task. Finally, we investigate aggression minimization by launching competitive cascades to “inform” and “heal” aggressors. We show that IC and LT models can be used in aggression minimization, providing less intrusive alternatives to the blocking techniques currently employed by Twitter.

Sign in / Sign up

Export Citation Format

Share Document