Matching Items (17)
Filtering by
- All Subjects: Twitter
- Creators: Walter Cronkite School of Journalism and Mass Communication
- Creators: Liu, Huan
Description
The increasing popularity of Twitter renders improved trustworthiness and relevance assessment of tweets much more important for search. However, given the limitations on the size of tweets, it is hard to extract measures for ranking from the tweet's content alone. I propose a method of ranking tweets by generating a reputation score for each tweet that is based not just on content, but also additional information from the Twitter ecosystem that consists of users, tweets, and the web pages that tweets link to. This information is obtained by modeling the Twitter ecosystem as a three-layer graph. The reputation score is used to power two novel methods of ranking tweets by propagating the reputation over an agreement graph based on tweets' content similarity. Additionally, I show how the agreement graph helps counter tweet spam. An evaluation of my method on 16~million tweets from the TREC 2011 Microblog Dataset shows that it doubles the precision over baseline Twitter Search and achieves higher precision than current state of the art method. I present a detailed internal empirical evaluation of RAProp in comparison to several alternative approaches proposed by me, as well as external evaluation in comparison to the current state of the art method.
ContributorsRavikumar, Srijith (Author) / Kambhampati, Subbarao (Thesis advisor) / Davulcu, Hasan (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Social media platforms such as Twitter, Facebook, and blogs have emerged as valuable
- in fact, the de facto - virtual town halls for people to discover, report, share and
communicate with others about various types of events. These events range from
widely-known events such as the U.S Presidential debate to smaller scale, local events
such as a local Halloween block party. During these events, we often witness a large
amount of commentary contributed by crowds on social media. This burst of social
media responses surges with the "second-screen" behavior and greatly enriches the
user experience when interacting with the event and people's awareness of an event.
Monitoring and analyzing this rich and continuous flow of user-generated content can
yield unprecedentedly valuable information about the event, since these responses
usually offer far more rich and powerful views about the event that mainstream news
simply could not achieve. Despite these benefits, social media also tends to be noisy,
chaotic, and overwhelming, posing challenges to users in seeking and distilling high
quality content from that noise.
In this dissertation, I explore ways to leverage social media as a source of information and analyze events based on their social media responses collectively. I develop, implement and evaluate EventRadar, an event analysis toolbox which is able to identify, enrich, and characterize events using the massive amounts of social media responses. EventRadar contains three automated, scalable tools to handle three core event analysis tasks: Event Characterization, Event Recognition, and Event Enrichment. More specifically, I develop ET-LDA, a Bayesian model and SocSent, a matrix factorization framework for handling the Event Characterization task, i.e., modeling characterizing an event in terms of its topics and its audience's response behavior (via ET-LDA), and the sentiments regarding its topics (via SocSent). I also develop DeMa, an unsupervised event detection algorithm for handling the Event Recognition task, i.e., detecting trending events from a stream of noisy social media posts. Last, I develop CrowdX, a spatial crowdsourcing system for handling the Event Enrichment task, i.e., gathering additional first hand information (e.g., photos) from the field to enrich the given event's context.
Enabled by EventRadar, it is more feasible to uncover patterns that have not been
explored previously and re-validating existing social theories with new evidence. As a
result, I am able to gain deep insights into how people respond to the event that they
are engaged in. The results reveal several key insights into people's various responding
behavior over the event's timeline such the topical context of people's tweets does not
always correlate with the timeline of the event. In addition, I also explore the factors
that affect a person's engagement with real-world events on Twitter and find that
people engage in an event because they are interested in the topics pertaining to
that event; and while engaging, their engagement is largely affected by their friends'
behavior.
- in fact, the de facto - virtual town halls for people to discover, report, share and
communicate with others about various types of events. These events range from
widely-known events such as the U.S Presidential debate to smaller scale, local events
such as a local Halloween block party. During these events, we often witness a large
amount of commentary contributed by crowds on social media. This burst of social
media responses surges with the "second-screen" behavior and greatly enriches the
user experience when interacting with the event and people's awareness of an event.
Monitoring and analyzing this rich and continuous flow of user-generated content can
yield unprecedentedly valuable information about the event, since these responses
usually offer far more rich and powerful views about the event that mainstream news
simply could not achieve. Despite these benefits, social media also tends to be noisy,
chaotic, and overwhelming, posing challenges to users in seeking and distilling high
quality content from that noise.
In this dissertation, I explore ways to leverage social media as a source of information and analyze events based on their social media responses collectively. I develop, implement and evaluate EventRadar, an event analysis toolbox which is able to identify, enrich, and characterize events using the massive amounts of social media responses. EventRadar contains three automated, scalable tools to handle three core event analysis tasks: Event Characterization, Event Recognition, and Event Enrichment. More specifically, I develop ET-LDA, a Bayesian model and SocSent, a matrix factorization framework for handling the Event Characterization task, i.e., modeling characterizing an event in terms of its topics and its audience's response behavior (via ET-LDA), and the sentiments regarding its topics (via SocSent). I also develop DeMa, an unsupervised event detection algorithm for handling the Event Recognition task, i.e., detecting trending events from a stream of noisy social media posts. Last, I develop CrowdX, a spatial crowdsourcing system for handling the Event Enrichment task, i.e., gathering additional first hand information (e.g., photos) from the field to enrich the given event's context.
Enabled by EventRadar, it is more feasible to uncover patterns that have not been
explored previously and re-validating existing social theories with new evidence. As a
result, I am able to gain deep insights into how people respond to the event that they
are engaged in. The results reveal several key insights into people's various responding
behavior over the event's timeline such the topical context of people's tweets does not
always correlate with the timeline of the event. In addition, I also explore the factors
that affect a person's engagement with real-world events on Twitter and find that
people engage in an event because they are interested in the topics pertaining to
that event; and while engaging, their engagement is largely affected by their friends'
behavior.
ContributorsHu, Yuheng (Author) / Kambhampati, Subbarao (Thesis advisor) / Horvitz, Eric (Committee member) / Krumm, John (Committee member) / Liu, Huan (Committee member) / Sundaram, Hari (Committee member) / Arizona State University (Publisher)
Created2014
Description
President Donald Trump announced his candidacy in June 2015, and the America immediately knew that he was an unorthodox candidate. Early on in his campaign, Trump isolated groups of people and treated them as enemies, but none so consistently as the news media. What began as criticism of "fake news," turned into calling the news media "the opposition party." However, media professionals agree that when the Trump administration called the news media the "enemy of the American people" \u2014 a line had been crossed. In the last two years Trump has denied simple fact and credible journalism countless times. His avid use of social media allows his messages to reach millions of people in moments - which had the potential to be a positive thing. However, Twitter is often where Trump turns to dispute the media, science, fact or anything else that "opposes" him. If Americans cannot believe the news media, cannot believe science, and cannot believe established fact, what can they believe? Allowing one man, in this case, Trump, to become the beacon of truth is dangerous and destructive to democracy. The news media must do their best to recapture the trust and faith of the American people by producing good, honest journalism. Seasoned journalism professionals say that his attacks on the media are likely a facade, just another way to appeal to his base, but that those attacks have the potential to wreak havoc in American society. Regardless of Trump's intentions, the toxicity between him and news media could have consequences that reach far beyond his presidency.
ContributorsPenningroth, Kendra Rene (Author) / Crane, Steve (Thesis director) / Downie, Leonard (Committee member) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / School of Criminology and Criminal Justice (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
Social media is used by people every day to discuss the nuances of their lives. Major League Baseball (MLB) is a popular sport in the United States, and as such has generated a great deal of activity on Twitter. As fantasy baseball continues to grow in popularity, so does the research into better algorithms for picking players. Most of the research done in this area focuses on improving the prediction of a player's individual performance. However, the crowd-sourcing power afforded by social media may enable more informed predictions about players' performances. Players are chosen by popularity and personal preferences by most amateur gamblers. While some of these trends (particularly the long-term ones) are captured by ranking systems, this research was focused on predicting the daily spikes in popularity (and therefore price or draft order) by comparing the number of mentions that the player received on Twitter compared to their previous mentions. In doing so, it was demonstrated that improved fantasy baseball predictions can be made through leveraging social media data.
ContributorsRuskin, Lewis John (Author) / Liu, Huan (Thesis director) / Montgomery, Douglas (Committee member) / Morstatter, Fred (Committee member) / Industrial, Systems (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
The foundations of legacy media, especially the news media, are not as strong as they once were. A digital revolution has changed the operation models for and journalistic organizations are trying to find their place in the new market. This project is intended to analyze the effects of new/emerging technologies on the journalism industry. Five different categories of technology will be explored. They are as follows: the semantic web, automation software, data analysis and aggregators, virtual reality and drone journalism. The potential of these technologies will be broken up according to four guidelines, ethical implications, effects on the reportorial process, business impacts and changes to the consumer experience. Upon my examination, it is apparent that no single technology will offer the journalism industry the remedy it has been searching for. Some combination of emerging technologies however, may form the basis for the next generation of news. Findings are presented on a website that features video, visuals, linked content, and original graphics. Website found at http://www.explorenewstech.com/
ContributorsMaxwell, Gavin William (Author) / McGuire, Tim (Thesis director) / Cornelius, David (Committee member) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / School of Politics and Global Studies (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
While Italian and American news may look similar from a surface observation, the history and the development of news practices in each respective country is very different. The intent of this research is to dissect the breaking news cycle and point out differences and offer an explanation as to why these differences exist. The research for this will be collected using a variety of methods including first-hand observation, interviews and photographs. It will require travel to the four Italian media locations that are being compared as well as historic research to be conducted in order to provide context for the study. What is collected at the various Italian media organizations will be compared with the American news outlets The Arizona Republic and Arizona NBC affiliate, 12 News. The study goals are focused around three main research questions that aim to uncover differences in breaking news practices regarding ethics, the reporting process and promotion using social media. Cultural, historic and physical barriers separate the two countries. Because of this, directly comparing breaking news between the locations will be difficult, thus it is crucial to be able to analyze what data are being gathered in order to uncover patterns and draw conclusions.
ContributorsNicosia, Domenico Giuseppe (Author) / Silcock, B. William (Thesis director) / Dell'Anna, Antonella (Committee member) / Johnson, Aric (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor) / School of Social and Behavioral Sciences (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor)
Created2014-05
Description
Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then we perform bot detection of our own. For our bot detection, we are interested in bots on Twitter that tweet Arabic extremist-like phrases. A testing dataset is collected using the honeypot method, and five different heuristics are measured for their effectiveness in detecting bots. The model underperformed, but we have laid the ground-work for a vastly untapped focus on bot detection: extremist ideal diffusion through bots.
ContributorsKarlsrud, Mark C. (Author) / Liu, Huan (Thesis director) / Morstatter, Fred (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2015-05
DescriptionThe purpose of this study is to assess to what degree employees of the Commercial Service are knowledgeable about social media. It is also a means to learn about the perceptions of social media within the U.S. government and the Commercial Service and examine its innovation culture.
ContributorsSinclair, Torunn Kathryn (Author) / Matera, Fran (Thesis director) / Phillips, Robin (Committee member) / Barrett, The Honors College (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor)
Created2014-05
Description
Although smaller and more local elections could have implications more dramatic to an individual than larger district-, state-, and nation-wide elections do, very few citizens vote in them. Moreover, citizens are limited in procuring further information on candidates, issues, and the overall election when there are fewer sources of such information across various mediums. While existing literature on political communication and voter participation does not yet extend far enough to sufficiently address the most local aspects of media effects on elections, the political science field’s dominating frameworks would suggest that an increase in news media, social media, and ground mobilization tactics would increase civic engagement and voter participation. My research, which focuses on hyperlocal elections, both supports andrefutes certain elements of that suggestion. Based on surveys of potential voters in a university’s student government election and a school board election, interviews with two student government presidential candidates, and an analysis of social media engagement, my research compares three mass media platforms and two elections to characterize the effects of media on hyperlocal elections—that certain tactics have drastically different results on different populations. My research expands the body of media and politics knowledge to include hyperlocal elections, suggesting that civic engagement on the local levels require increased further study.
ContributorsRomanov, Andrew Samuilovich (Author) / Wells, David (Thesis director) / Brodie, Mark (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor) / Department of English (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / School of Politics and Global Studies (Contributor)
Created2015-05
Description
The format for news has been in a state of evolution since it was introduced to the online platform. Given this digital space for creative freedom, some journalists have ventured towards producing original video content specifically for online. The issue that arises with this content is that there is no widely accepted, perceivable structure for the format, unlike other news mediums (i.e.- print journalism, broadcast journalism). This thesis takes an in-depth look at an online video news experiment conducted at Arizona State University's student news organization, the State Press, with the intention to understand the viability of the project and online video news as a whole and to offer a set of guidelines that could direct a student media organization in the creation of such content.
ContributorsJeffrey, Courtland Emmett (Author) / Manning, Jason (Thesis director) / Roschke, Kristy (Committee member) / Barrett, The Honors College (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor)
Created2015-05