Matching Items (6)
Filtering by
- All Subjects: Social Media
- Genre: Masters Thesis
- Creators: Davulcu, Hasan
- Creators: Mickelson, Kristin
- Member of: ASU Electronic Theses and Dissertations
- Member of: Theses and Dissertations
- Status: Published
Description
Social media has become a primary means of communication and a prominent source of information about day-to-day happenings in the contemporary world. The rise in the popularity of social media platforms in recent decades has empowered people with an unprecedented level of connectivity. Despite the benefits social media offers, it also comes with disadvantages. A significant downside to staying connected via social media is the susceptibility to falsified information or Fake News. Easy accessibility to social media and lack of truth verification tools favored the miscreants on online platforms to spread false propaganda at scale, ensuing chaos. The spread of misinformation on these platforms ultimately leads to mistrust and social unrest. Consequently, there is a need to counter the spread of misinformation which could otherwise have a detrimental impact on society. A notable example of such a case is the 2019 Covid pandemic misinformation spread, where coordinated misinformation campaigns misled the public on vaccination and health safety. The advancements in Natural Language Processing gave rise to sophisticated language generation models that can generate realistic-looking texts. Although the current Fake News generation process is manual, it is just a matter of time before this process gets automated at scale and generates Neural Fake News using language generation models like the Bidirectional Encoder Representations from Transformers (BERT) and the third generation Generative Pre-trained Transformer (GPT-3). Moreover, given that the current state of fact verification is manual, it calls for an urgent need to develop reliable automated detection tools to counter Neural Fake News generated at scale. Existing tools demonstrate state-of-the-art performance in detecting Neural Fake News but exhibit a black box behavior. Incorporating explainability into the Neural Fake News classification task will build trust and acceptance amongst different communities and decision-makers. Therefore, the current study proposes a new set of interpretable discriminatory features. These features capture statistical and stylistic idiosyncrasies, achieving an accuracy of 82% on Neural Fake News classification. Furthermore, this research investigates essential dependency relations contributing to the classification process. Lastly, the study concludes by providing directions for future research in building explainable tools for Neural Fake News detection.
ContributorsKarumuri, Ravi Teja (Author) / Liu, Huan (Thesis advisor) / Corman, Steven (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2022
Description
With its ever-increasing prevalence throughout the world, social media use has become a primary means of communication and connection with others. Much research has been dedicated to the topic of social media use, suggesting both positive and negative outcomes for those who are online more frequently. While uploading content and interacting with posts that others have created is associated with social comparison and identity formation, there is little research to date that examines the relationship between social media use and an individual’s meaning in life. One of the greater benefits of social media use is the ease with which people can curate their own personal identities, and this has led to an increase in users—particularly young adults—posting sexualized images of themselves for social gain. Untested in prior research is the relationship between self-objectification via social media and life meaning. For my thesis, I proposed a moderation model in which participants who reported higher levels of self-objectified beliefs and online habits would also report lower levels of meaning in life. Furthermore, I hypothesized that there would be unique differences between genders and sexual orientations that would also serve as moderators, such that heterosexual women and LGBQ men would demonstrate the lowest levels of life meaning when reporting high levels of self-objectification. Results from analyses found that while there was no significant relationship between active social media use and meaning in life, there was a significant three-way interaction between objectified social media use, gender and sexual orientation, and meaning. Findings from this study provide support for previous research that has found LGBQ men and heterosexual women face the most adverse effects from self-objectification. These results suggest that self-objectified social media use can negatively impact life meaning for certain populations.
ContributorsMostoller, Alexis (Author) / Mickelson, Kristin (Thesis advisor) / Salerno, Jessica (Committee member) / Burleson, Mary (Committee member) / Arizona State University (Publisher)
Created2022
Description
Social media platforms have become widely used for open communication, yet their lack of moderation has led to the proliferation of harmful content, including hate speech. Manual monitoring of such vast amounts of user-generated data is impractical, thus necessitating automated hate speech detection methods. Pre-trained language models have been proven to possess strong base capabilities, which not only excel at in-distribution language modeling but also show powerful abilities in out-of-distribution language modeling, transfer learning and few-shot learning. However, these models operate as complex function approximators, mapping input text to a hate speech classification, without providing any insights into the reasoning behind their predictions. Hence, existing methods often lack transparency, hindering their effectiveness, particularly in sensitive content moderation contexts. Recent efforts have been made to integrate their capabilities with large language models like ChatGPT and Llama2, which exhibit reasoning capabilities and broad knowledge utilization. This thesis explores leveraging the reasoning abilities of large language models to enhance the interpretability of hate speech detection. A novel framework is proposed that utilizes state-of-the-art Large Language Models (LLMs) to extract interpretable rationales from input text, highlighting key phrases or sentences relevant to hate speech classification. By incorporating these rationale features into a hate speech classifier, the framework inherently provides transparent and interpretable results. This approach combines the language understanding prowess of LLMs with the discriminative power of advanced hate speech classifiers, offering a promising solution to the challenge of interpreting automated hate speech detection models.
ContributorsNirmal, Ayushi (Author) / Liu, Huan (Thesis advisor) / Davulcu, Hasan (Committee member) / Wei, Hua (Committee member) / Arizona State University (Publisher)
Created2024
Description
Social media has been extensively researched, and its effects on well-being are well established. What is less studied, however, is how social media affects romantic relationships specifically. The few studies that have researched this have found mixed results. Some researchers have found social media to have a positive influence on relationship outcomes, while other have found social media to have a negative influence. In an attempt to reconcile these discrepancies, the current thesis study explored possible mediators between social media use and relationship health outcomes which, to my knowledge, has not been investigated in previous literature. Three moderators were explored: type of social media use (active use versus passive use), relationship-contingent self-esteem, and social comparison orientation. The baseline portion of the study had 547 individuals, recruited from Arizona State University’s SONA system as well as Amazon’s Mechanical Turk, who were in a romantic relationship for at least three months; the follow-up portion of the study had 181 participants. Results suggest that women who passively use social media exhibit a negative association between hours per day of social media use and baseline relationship satisfaction. Men who passively use social media exhibited a negative association between hours per day of social media use and follow-up relationship satisfaction, as well as a negative association with baseline commitment. While relationship-contingent self-esteem did not moderate the association between hours per day of social media use and relationship health, it was positively related to both men and women’s baseline relationship satisfaction and baseline commitment. Social comparison orientation (SCO) produced minimal results; women low on SCO exhibited a negative association between social media use and baseline relationship satisfaction, and higher SCO for men was associated with lower baseline commitment. Finally, exploratory post-hoc mediation models revealed that relationship comparisons mediated the association between hours per day of social media use and baseline relationship, as well as baseline commitment, for both men and women. Previous research supports the findings regarding passive social media use, while the findings regarding relationship-contingent self-esteem and relationship comparisons add new findings to the romantic relationship literature.
ContributorsQuiroz, Selena (Author) / Mickelson, Kristin (Thesis advisor) / Burleson, Mary (Committee member) / Halavais, Alexander (Committee member) / Arizona State University (Publisher)
Created2019
Description
Proliferation of social media websites and discussion forums in the last decade has resulted in social media mining emerging as an effective mechanism to extract consumer patterns. Most research on social media and pharmacovigilance have concentrated on
Adverse Drug Reaction (ADR) identification. Such methods employ a step of drug search followed by classification of the associated text as consisting an ADR or not. Although this method works efficiently for ADR classifications, if ADR evidence is present in users posts over time, drug mentions fail to capture such ADRs. It also fails to record additional user information which may provide an opportunity to perform an in-depth analysis for lifestyle habits and possible reasons for any medical problems.
Pre-market clinical trials for drugs generally do not include pregnant women, and so their effects on pregnancy outcomes are not discovered early. This thesis presents a thorough, alternative strategy for assessing the safety profiles of drugs during pregnancy by utilizing user timelines from social media. I explore the use of a variety of state-of-the-art social media mining techniques, including rule-based and machine learning techniques, to identify pregnant women, monitor their drug usage patterns, categorize their birth outcomes, and attempt to discover associations between drugs and bad birth outcomes.
The technique used models user timelines as longitudinal patient networks, which provide us with a variety of key information about pregnancy, drug usage, and post-
birth reactions. I evaluate the distinct parts of the pipeline separately, validating the usefulness of each step. The approach to use user timelines in this fashion has produced very encouraging results, and can be employed for a range of other important tasks where users/patients are required to be followed over time to derive population-based measures.
Adverse Drug Reaction (ADR) identification. Such methods employ a step of drug search followed by classification of the associated text as consisting an ADR or not. Although this method works efficiently for ADR classifications, if ADR evidence is present in users posts over time, drug mentions fail to capture such ADRs. It also fails to record additional user information which may provide an opportunity to perform an in-depth analysis for lifestyle habits and possible reasons for any medical problems.
Pre-market clinical trials for drugs generally do not include pregnant women, and so their effects on pregnancy outcomes are not discovered early. This thesis presents a thorough, alternative strategy for assessing the safety profiles of drugs during pregnancy by utilizing user timelines from social media. I explore the use of a variety of state-of-the-art social media mining techniques, including rule-based and machine learning techniques, to identify pregnant women, monitor their drug usage patterns, categorize their birth outcomes, and attempt to discover associations between drugs and bad birth outcomes.
The technique used models user timelines as longitudinal patient networks, which provide us with a variety of key information about pregnancy, drug usage, and post-
birth reactions. I evaluate the distinct parts of the pipeline separately, validating the usefulness of each step. The approach to use user timelines in this fashion has produced very encouraging results, and can be employed for a range of other important tasks where users/patients are required to be followed over time to derive population-based measures.
ContributorsChandrashekar, Pramod Bharadwaj (Author) / Davulcu, Hasan (Thesis advisor) / Gonzalez, Graciela (Thesis advisor) / Hsiao, Sharon (Committee member) / Arizona State University (Publisher)
Created2016
Description
The development of the internet provided new means for people to communicate effectively and share their ideas. There has been a decline in the consumption of newspapers and traditional broadcasting media toward online social mediums in recent years. Social media has been introduced as a new way of increasing democratic discussions on political and social matters. Among social media, Twitter is widely used by politicians, government officials, communities, and parties to make announcements and reach their voice to their followers. This greatly increases the acceptance domain of the medium.
The usage of social media during social and political campaigns has been the subject of a lot of social science studies including the Occupy Wall Street movement, The Arab Spring, the United States (US) election, more recently The Brexit campaign. The wide
spread usage of social media in this space and the active participation of people in the discussions on social media made this communication channel a suitable place for spreading propaganda to alter public opinion.
An interesting feature of twitter is the feasibility of which bots can be programmed to operate on this platform. Social media bots are automated agents engineered to emulate the activity of a human being by tweeting some specific content, replying to users, magnifying certain topics by retweeting them. Network on these bots is called botnets and describing the collaboration of connected computers with programs that communicates across multiple devices to perform some task.
In this thesis, I will study how bots can influence the opinion, finding which parameters are playing a role in shrinking or coalescing the communities, and finally logically proving the effectiveness of each of the hypotheses.
The usage of social media during social and political campaigns has been the subject of a lot of social science studies including the Occupy Wall Street movement, The Arab Spring, the United States (US) election, more recently The Brexit campaign. The wide
spread usage of social media in this space and the active participation of people in the discussions on social media made this communication channel a suitable place for spreading propaganda to alter public opinion.
An interesting feature of twitter is the feasibility of which bots can be programmed to operate on this platform. Social media bots are automated agents engineered to emulate the activity of a human being by tweeting some specific content, replying to users, magnifying certain topics by retweeting them. Network on these bots is called botnets and describing the collaboration of connected computers with programs that communicates across multiple devices to perform some task.
In this thesis, I will study how bots can influence the opinion, finding which parameters are playing a role in shrinking or coalescing the communities, and finally logically proving the effectiveness of each of the hypotheses.
ContributorsAhmadi, Mohsen (Author) / Davulcu, Hasan (Thesis advisor) / Sen, Arunabha (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2020