Social Media Commons^™

Classifying Misogynistic Tweets Using A Blended Model: The Ami Shared Task In Ibereval 2018, John Cardiff, Elena Shushkevich

Conference Papers

This article describes a possible solution for Automatic Misogyny Identification (AMI) Shared Task at IBEREVAL-2018. The proposed technique is based on combining several simpler classifiers into one more complex blended model, which classified the data taking into account the probabilities of belonging to classes calculated by simpler models. We used the Logistic Regression, Naive Bayes, and SVM classifiers. The experimental results show that blended model works better than simpler models for all three type of classification, for both binomial classification (Misogyny Identifivation, Target Classification) and multinomial classification (Misogynistic Behavior).

Offline Versus Online: A Meaningful Categorization Of Ties For Retweets, Felicia Natali, Feida Zhu

Research Collection School Of Computing and Information Systems

With the recent proliferation of news being shared through online social networks, it is crucial to determine how news is spread and what drives people to share certain stories. In this paper, we focus on the social networking site Twitter and analyse user’s retweets. We study retweeting patterns between offline and online friends, particularly, how tweet novelty and tweet topic differ between tweets retweeted by offline friends and those retweeted by online friends.

Exploring Offline Friendships On The Social Information Network: Network Characteristics, Information Diffusion, And Tie Strength, Felicia Natali

Dissertations and Theses Collection (Open Access)

The rapid increase in online social networking services over the last decade has pre- sented an unprecedented opportunity to observe users’ behaviour both on a societal and individual level. The insight gained from analysing such data can help foster a deeper understanding of social media users and the flow of information, while also offering valuable business applications. User relationships are among the most studied aspects of online behaviour. These relationships are not homogeneous. Past research has shown that people use social networks to both socialize and source in- formation. Hence, different types of links – used to socialize, gain information, …

Temporal And Spatiotemporal Investigation Of Tourist Attraction Visit Sentiment On Twitter, Jose J. Padilla, Hamdi Kavak, Christopher J. Lynch, Ross J. Gore, Saikou Y. Diallo

VMASC Publications

In this paper, we propose a sentiment-based approach to investigate the temporal and spatiotemporal effects on tourists' emotions when visiting a city's tourist destinations. Our approach consists of four steps: data collection and preprocessing from social media; visitor origin identification; visit sentiment identification; and temporal and spatiotemporal analysis. The temporal and spatiotemporal dimensions include day of the year, season of the year, day of the week, location sentiment progression, enjoyment measure, and multi-location sentiment progression. We apply this approach to the city of Chicago using over eight million tweets. Results show that seasonal weather, as well as special days and …

Coming Together Around Hashtags: Exploring The Formation Of Digital Emergent Citizen Groups, Andrew S. Pyle, Brandon Boatwright

Publications

It has been well established that during and after crisis or emergency events, groups of citizens come together to help one another, solve problems, and manage recovery or cleanup. These groups are called emergent citizen groups. They form organically and often disband when the emergency is managed. This study proposes that similar types of groups now form in digital spaces during and after crises. The authors studied conversation on Twitter that used the hashtag “#PrayforUSC” after the murder-suicide that took place at the University of South Carolina in 2015. Initial results indicate that hashtags can function as focal points or …

Explaining Animosity Towards The Roma: A Case Study Of Twitter Communication In Italy During The Refugee Crisis, Mayuko Nakatsuka

Dissertations, Theses, and Capstone Projects

Italy is known for hostile treatment of the Roma, one of the largest ethnic minority groups in Europe. This paper seeks to understand what is causing Italians to talk negatively about the Roma on Twitter. Statistical analysis is performed utilizing the data mined from Twitter along with other variables. The study finds that Roma population, foreign population, and number of refugees all have significant effects on the total number of tweets or the average negative sentiment of tweets. The results indicate that native Italians may group minority groups all together and regard them as “others”. Although the research design has …

How College Campuses Are Using Social Media During Severe Weather Events, Emmale Davis

Graduate Theses and Dissertations

This study explores how college campuses are using social media during severe weather events. This topic surfaced after a tornado devastated Moore, Oklahoma in May 2013 and those displaced flocked to the University of Oklahoma campus after a post made on Twitter went viral prior to an official message being sent out by the university. In order to further explore this topic, a qualitative phenomenological case study was conducted at the following sites: University of Alabama, Missouri Southern State University, University of Oklahoma, and Florida State University. This study included observations of social media posts on Facebook and Twitter on …

Political Journalists Tweet About The Final 2016 Presidential Debate, Hannah Hopper

Electronic Theses and Dissertations

Past research shows that journalists are gatekeepers to information the public seeks. Using the gatekeeping and agenda-setting theory, this study used a content analysis of tweets from political journalists during the final 2016 presidential debate to examine social media usage in efforts to convey information to followers and whether social media has allowed for journalists to present a more transparent view of candidates to the public. This study used feminist political theory to further analyze whether the tweets from political journalists portrayed Hillary Clinton, the female candidate, with stereotypical “female” traits, such as more emotional and more trustworthy. Applying these …

Social Media: On Tech-Caves, Virtual Panopticism, And The Science Fiction-Like State In Which We Unwittingly Find Ourselves, Michael Major

Theses

Making use of three historic philosophical thought experiments, this paper blends psychological perspectives with philosophical reasoning to show how social media is corrupting our perception of reality, the result of which is ultimately detrimental to society as a whole. This is accomplished by first using Plato’s “Allegory of the Cave” to analyze and discuss the ways in which social media is limiting humanity’s access to real knowledge. Next, Michel Foucault’s analysis of punishment in its social context, Discipline and Punish, is used to discuss the ways in which social media is adversely affecting our behavior. Finally, Robert Nozick’s “Experience …

Revisiting Image Of The City In Cyberspace: Analysis Of Spatial Twitter Messages During A Special Event, Junfeng Jiao, Michael Holmes, Greg P. Griffin

Research Collection College of Integrative Studies

This research investigated people’s communication of urban space as reflected in Twitter messages (tweets) during the 2012 Super Bowl. The authors archived over 600,000 tweets related to the Super Bowl from January 23 through early February 6. The authors identified 78 Indianapolis-area places or routes named in the tweets. Based on occurrence of these terms, the authors retained 9,103 city-specific messages for analysis. The frequency of such tweets changed over the two-week period and peaked two days before game day. Instances of all of Lynch’s (1960) The Image of the City elements (node, district, landmark, path, and edge) were found …

#Whitegenocide, The Alt-Right And Conspiracy Theory: How Secrecy And Suspicion Contributed To The Mainstreaming Of Hate, Andrew F. Wilson

Secrecy and Society

This article considers the relationship between “hashtag activism” as it is currently being used by the alt-right and the tendency to draw on conspiracy theory that Richard Hofstadter identified as being prevalent among what he termed “pseudo-conservatives” half a century earlier. Both the alt-right and Hofstadter’s “pseudo-conservatives” can be characterised by a pronounced populist nationalism that understands its aims as protecting a particular way of life whilst drawing on an aggrieved sense of injustice at being conspired against by an unseen enemy. That this “enemy” is typically foreign in actuality or in spirit confirms the cultural dimension on which their …

The Alt-Right's Use Of President Donald Trump's Twitter Account As A Propaganda Device, Erin Nicole Jorden

Theses, Dissertations and Capstones

The long campaign to repeal and replace the Affordable Care Act situated President Donald J. Trump in a context where attacks on President Barack Obama’s signature legislation symbolized a broader repudiation of his legacy. Even more than mainstream Republican partisans, the altright blogosphere celebrated the demise of the law to symbolically cleanse the nation of Obama’s influence. Trump attempted to honor his pledge to end Obamacare in his first year of office with his support of the American Health Care Act (March 2017), Better Care Reconciliation Act (July 2017), and the Graham-Cassidy Bill (September 2017). Members of the alt-right reframed …

Examining Twitter Content Of State Emergency Management During Hurricane Joaquin, Adam M. Rainear, Kenneth A. Lachlan, Anne Oeldorf-Hirsch, Christina Devoss

2018 Faculty Bibliography

Those tasked with disseminating life-protecting messages during crises have many factors to consider. Social media sites have become an information source for individuals during these times, and more research is needed examining the use of specific message strategies by emergency management agencies that may elicit attention and retransmission. This study examines Twitter content concerning Hurricane Joaquin. Content analysis of tweets from state emergency management accounts was performed to provide an overview of the content and stylistic elements used in tweets associated with the event. The findings are discussed in the context of both past research on the matter and implications …

"The 100" And The Social Contract Of Social Tv, Myles Mcnutt

Communication & Theatre Arts Faculty Publications

I explore how the controversy surrounding an LGBT storyline on The 100 (2014–) points to the shifting social contracts of social media engagement between fans and the TV industry, as well as the challenges faced by fans and critics who attempted to solidify that contract in the wake of said controversy.

Teacher Twitter Chats: Gender Differences In Participants’ Contributions, Stacey L. Kerr, Mardi J. Schmeichel

Department of Teaching, Learning, and Teacher Education: Faculty Publications

Gender differences in participation were examined across four Twitter chats for social studies teachers. Analyses drawing on mixed methods revealed that while there was parity across most kinds of tweets, participants identified as men were more likely to use the examined Twitter chats to share resources, give advice, boast, promote their own blog/resource/website, and offer critique to another participants’ tweet. Participants identified as women were more likely to write tweets that included positive affirmations for other chat participants. These findings suggest that there are differences in the way that women and men tend to participate in teacher Twitter chat spaces.

Delving Into The Specificity Of Instructional Guidance In Social Media-Supported Learning Environments, Tian Luo

STEMPS Faculty Publications

Aim/Purpose: This study investigates the variations in student participation patterns across different types of instructional activities, learning modes, and with different instructional guidance approaches. In the current study, different variables, modes of learning (guided versus unguided), and types of guidance (social versus cognitive) were manipulated in a series of microblogging-supported collaborative learning tasks to examine to what extent and in which aspects instructional guidance affects the effectiveness and student perception of microblogging-supported learning.

Background: Despite the overwhelming agreement on the importance of instructional guidance in microblogging-supported learning environments, very few studies have been done to examine the specificity of guidance, …

Repackaging The Reach Of Dreams: News Coverage Of Daca Rescindment By Three National Newspapers On Twitter, Megan Pietruszewski

Dissertations, Master's Theses and Master's Reports

This thesis examines the frames used by three news organizations to cover the rescindment of the Deferred Action for Childhood Arrivals (DACA) program. The rescindment of DACA was a pivotal transition period open to new immigration policy, and frames used in the news coverage of DACA are important as frames influence public opinion and possible future immigration policy. This study uses corpus linguistic methods and Van Gorp’s inductive framing analysis to explore how a complex political decision like DACA rescindment is covered in condensed news stories on Twitter as well as in full-length news articles. The Executive Critique frame, which …

Inferring Social Media Users’ Demographics From Profile Pictures: A Face++ Analysis On Twitter Users, Soon-Gyo Jung, Jisun An, Haewoon Kwak, Joni Salminen, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

In this research, we evaluate the applicability of using facial recognition of social media account profile pictures to infer the demographic attributes of gender, race, and age of the account owners leveraging a commercial and well-known image service, specifically Face++. Our goal is to determine the feasibility of this approach for actual system implementation. Using a dataset of approximately 10,000 Twitter profile pictures, we use Face++ to classify this set of images for gender, race, and age. We determine that about 30% of these profile pictures contain identifiable images of people using the current state-of-the-art automated means. We then employ …

Weather Communication On Twitter: Identifying Popular Content And Optimal Warning Format Via Case Studies And A Survey Analysis, Joshua D. Eachus

LSU Doctoral Dissertations

The use of Twitter as a channel for weather information inspires a deeper analysis of key information nodes during episodes of high impact weather, especially local meteorologists. To optimize communication on the channel, it is important to understand what kinds of messages produce exposure and attention among users—which translates to knowledge that could improve the reach of a warning. Literature identifies two key models that well describe the cognitive processing of tweets and warnings. The Protective Action Decision Model (PADM) describes risk perception and the factors that enable or disable one from acting on a warning. Particularly through environmental and …

An Analysis Of Rumor And Counter-Rumor Messages In Social Media, Dion Hoe-Lian Goh, Alton Y. K. Chua, Hanyu Shi, Wenju Wei, Haiyan Wang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Social media platforms are one of the fastest ways to disseminate information but they have also been used as a means to spread rumors. If left unchecked, rumors have serious consequences. Counter-rumors, messages used to refute rumors, are an important means of rumor curtailment. The objective of this paper is to examine the types of rumor and counter-rumor messages generated in Twitter in response to the falsely reported death of a politician, Lee Kuan Yew, who was Singapore’s first Prime Minister. Our content analysis of 4321Twitter tweets about Lee’s death revealed six categories of rumor messages, four categories ofcounter-rumor messages …

Googalization: The Response To A “Friend Request” In The Workplace, Ashley Harrington

The Eastern Illinois University Political Science Review

With social networking taking over the lives and time of its users, workplace time and productivity appear to be neglected and decreasing. However, perhaps online social networking is just a plan that has yet to make its inclusion into the workplace. Within this context, the author considers both the positives and negatives associated with social networking in the workplace.

Is Every Tweet Created Equal? A Framework To Identify Relevant Tweets For Business Research, Thad Chee

Information Technology & Decision Sciences Theses & Dissertations

It is a life or death matter for a firm to observe its environment and identify new threats or opportunities quickly. Information technology has increased firm’s speed and agility in responding to environmental changes. Social media offers a vast and timely source of environmental information that firms can readily use gauge public sentiment. Twitter is a high-speed service that allows anyone to “tweet” a message to any interested parties. Firms can access near instantaneous changes in the public mood about any topic by using Sentiment Analysis. These topics range from predicting equities prices to predicting election outcomes. A gap exists …

Trolling Twitter, Eric Vorst

Dissertations

Political polarization is a defining feature of the contemporary American political landscape. While there is little doubt that elite polarization levels have risen dramatically in recent decades, there is some debate over the existence of a corresponding rise in mass polarization. Recent scholarship on mass polarization has cited evidence related to citizens’ positions on public policy issues, party sorting, and geographic polarization; however, questions remain as to the nature and extent of mass polarization in online spaces. Specifically, more needs to be known regarding how expressions of elite polarization influence the formation of polarized communities within social media.

This dissertation …

Advancing Democracy One Tweet At A Time, Landon T. Hester

LSU Master's Theses

This thesis takes a broad look how citizens use social media to foster political discussion, enhance political knowledge and engage in political participation in the United States. In this study, democracy is broken down into three empirically measurable components: political discussion, knowledge and participation. To begin, I provide an in-­‐depth review of past research examining the impact social media has on each element of democracy. In addition, I analyze data collected from a novel social media panel of 3,811 Twitter users by researchers from Louisiana State University (Davis et. al, 2017). From this, I measure the impact that Facebook and …

Demographics Of News Sharing In The U.S. Twittersphere, Julio C.S. Reis, Haewoon Kwak, Jisun An, Johnnatan Messias, Benevenuto Fabrıcio.

Research Collection School Of Computing and Information Systems

The widespread adoption and dissemination of online news through social media systems have been revolutionizing many segments of our society and ultimately our daily lives. In these systems, users can play a central role as they share content to their friends. Despite that, little is known about news spreaders in social media. In this paper, we provide the first of its kind in-depth characterization of news spreaders in social media. In particular, we investigate their demographics, what kind of content they share, and the audience they reach. Among our main findings, we show that males and white users tend to …

Effects Of Para-Social Presence On The Consumer Decision Journey, Ayda Tahmasbi

Communication Studies

Para-social presence is investigated in this research study to determine its effects on the consumer decision journey. Attachment styles are also taken into consideration as a possible influence on establishing para-social presence. This study specifically looks at an internet personality’s social media platforms, Twitter, Instagram, and YouTube, and her social media marketing efforts for the release of her new book, Almost Adulting. This study found statistically significant relationships between increasing level of para-social presence across Twitter, Instagram, and YouTube. Further, the study found that para-social presence has a positive correlation with consumers’ initial consideration, purchase decision, and post-purchase experience. Finally, …

The Retransmission Of Rumor And Rumor Correction Messages On Twitter, Alton Y. K. Chua, Cheng-Ying Tee, Augustine Pang, Ee-Peng Lim

Research Collection Lee Kong Chian School Of Business

This article seeks to examine the relationships among source credibility, message plausibility, message type (rumor or rumor correction) and retransmission of tweets in a rumoring situation. From a total of 5,885 tweets related to the rumored death of the founding father of Singapore Lee Kuan Yew, 357 original tweets without an “RT” prefix were selected and analyzed using negative binomial regression analysis. The results show that source credibility and message plausibility are correlated with retransmission. Also, rumor correction tweets are retweeted more than rumor tweets. Moreover, message type moderates the relationship between source credibility and retransmission as well as that …

Messaging Without A Message: Executive Value And Social Media Activity, Ru Gao, Gilles Hilary, Rencheng Wang

Research Collection School Of Accountancy

We show that executives who start tweeting benefit from better career options. We motivate this finding using the well-established theory of limited attention. Consistent with this explanation, we find that content is irrelevant. Comparative statics are also consistent with our framework. In particular, the effect of Twitter is greater for executives who were largely unrecognized and who were underpaid before they started tweeting, who garner greater public attention from their social media activity, who enjoy higher professional mobility, and who operate in environments where compensation setting is less structured.

Impact Of Cybvervetting On Job Seekers' Social Media Use And Identity Creation, Courtney Powers

Master's Theses (2009 -)

Social media has become an integral part of connecting with others and sharing personal information. As more individuals use social media to express themselves, organizations have begun using these same sites to make hiring decisions in a process called cybervetting. Although some researchers suggest that cybervetting has consequences for self-expression, currently little research has explored how cybervetting impacts job seekers’ social media use and identity creation. Accordingly, this study uses quantitative and qualitative methods to explore how cybervetting impacts job seekers’ social media use and online identity creation. By surveying job-seeking social media users, this study measures the relationships between …

Digital Fanbases: How The Athletic Department In The Ohio Athletic Conference Engage With Audiences, Dale Armbruster

Masters Essays

Research has long sought to define and quantify the component of relationships within strategic public relations management. With the development of social media, public relations practitioners have new methods to employ in building and maintaining two-way relationships with audiences and key publics. This study is intended to expand upon current organization-management research and identify best practices for athletic departments seeking to engage with their audiences. The development of organization-public models is detailed, along with historical application of the concept to athletics. Analysis of Twitter data revealed common themes among athletic departments that engage audiences successfully. The study concludes with a …