Matching Items (2)
Filtering by
- Member of: ASU Electronic Theses and Dissertations
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
Given the major investment young people make in earning and maintaining a peer reputation, our goal in this study was to explore the association between dimensions of negative and positive peer reputation in middle school and adjustment several years later, by the end of high school, among upper middle class youth. Prior research has shown negative reputations such as aggressive-disruptive and sensitive-isolated to be associated with maladjustment later in life, whereas reputations like popular and prosocial-leader have been related to positive future outcomes. However, there are contrary findings that reveal a more complex relationship between peer reputation and adjustment, showing certain “negative” reputations to be tied with better outcomes in some domains and the converse in others. Using a sample of middle school students, a confirmatory factor analysis (CFA) was performed to test a four-factor model of the Revised Class Play, a peer report measure on peer reputations. CFA findings supported the four-factor model with the following reputations: popular, prosocial, aggressive, and isolated. Structural equation models were used to predict 12th grade adjustment outcomes (academic achievement, psychopathology, substance use) from middle school peer reputation. Prosocial reputation in middle school was connected to higher academic achievement and fewer externalizing symptoms in 12th grade. Both prosocial and isolated peer reputation were negatively associated with alcohol, cigarette, and marijuana use, whereas a popular reputation was related to higher levels of alcohol use. Middle school reputation did not predict internalizing symptoms in 12th grade. Findings are discussed in terms of adaptive and maladaptive adjustment outcomes associated with each peer reputation and implications for future research.
ContributorsCurlee, Alexandria (Author) / Luthar, Suniya (Thesis advisor) / Aiken, Leona (Committee member) / Infurna, Frank (Committee member) / Arizona State University (Publisher)
Created2016