Matching Items (3)
Filtering by
- Genre: Masters Thesis
Description
In supervised learning, machine learning techniques can be applied to learn a model on
a small set of labeled documents which can be used to classify a larger set of unknown
documents. Machine learning techniques can be used to analyze a political scenario
in a given society. A lot of research has been going on in this field to understand
the interactions of various people in the society in response to actions taken by their
organizations.
This paper talks about understanding the Russian influence on people in Latvia.
This is done by building an eeffective model learnt on initial set of documents
containing a combination of official party web-pages, important political leaders' social
networking sites. Since twitter is a micro-blogging site which allows people to post
their opinions on any topic, the model built is used for estimating the tweets sup-
porting the Russian and Latvian political organizations in Latvia. All the documents
collected for analysis are in Latvian and Russian languages which are rich in vocabulary resulting into huge number of features. Hence, feature selection techniques can
be used to reduce the vocabulary set relevant to the classification model. This thesis
provides a comparative analysis of traditional feature selection techniques and implementation of a new iterative feature selection method using EM and cross-domain
training along with supportive visualization tool. This method out performed other
feature selection methods by reducing the number of features up-to 50% along with
good model accuracy. The results from the classification are used to interpret user
behavior and their political influence patterns across organizations in Latvia using
interactive dashboard with combination of powerful widgets.
a small set of labeled documents which can be used to classify a larger set of unknown
documents. Machine learning techniques can be used to analyze a political scenario
in a given society. A lot of research has been going on in this field to understand
the interactions of various people in the society in response to actions taken by their
organizations.
This paper talks about understanding the Russian influence on people in Latvia.
This is done by building an eeffective model learnt on initial set of documents
containing a combination of official party web-pages, important political leaders' social
networking sites. Since twitter is a micro-blogging site which allows people to post
their opinions on any topic, the model built is used for estimating the tweets sup-
porting the Russian and Latvian political organizations in Latvia. All the documents
collected for analysis are in Latvian and Russian languages which are rich in vocabulary resulting into huge number of features. Hence, feature selection techniques can
be used to reduce the vocabulary set relevant to the classification model. This thesis
provides a comparative analysis of traditional feature selection techniques and implementation of a new iterative feature selection method using EM and cross-domain
training along with supportive visualization tool. This method out performed other
feature selection methods by reducing the number of features up-to 50% along with
good model accuracy. The results from the classification are used to interpret user
behavior and their political influence patterns across organizations in Latvia using
interactive dashboard with combination of powerful widgets.
ContributorsBollapragada, Lakshmi Gayatri Niharika (Author) / Davulcu, Hasan (Thesis advisor) / Sen, Arunabha (Committee member) / Hsiao, Ihan (Committee member) / Arizona State University (Publisher)
Created2016
Description
Political party identification has an immense influence on shaping individual attitudes and processes of reasoning to the point where otherwise knowledgeable people endorse political conspiracies that support one's political in-group and simultaneously disparage an out-group. Although recent research has explored this tendency among partisans, less is known about how Independents respond in comparison. Previous research fails to identify the Independent as a unique type of voter, but rather categorizes this group as ostensibly partisan, not a separate phenomenon to investigate. However, most Independents purport neutrality and, by recent polls, are becoming a substantial body worthy of concerted focus. Many questions arise about who Independents really are. For example, do all who identify as Independent behave in a similar manner? Are Independents ideologically different than what is represented by a partisan label? Is the Independent category a broad term for something entirely misunderstood? A thorough investigation into the greater dynamics of the political environment in the United States is an enormous undertaking, requiring a robust interdisciplinary approach beyond the focus and intent of this study. Therefore, this study begins the journey toward understanding these phenomena; do Independents, as a whole, uniformly respond to statements about political conspiracy theories? To explore these possibilities, explicit responses are bypassed to evaluate the implicit appeal of political conspiracy theories. An action dynamics (mouse-tracking) approach, a data rich method that records the response process, demonstrates Independents are not in fact a homogeneous group, but rather seem to fall into two groups: non-partisan leaning and partisan leaning. The analysis exposes that relative to the baseline and control stimuli: (1) Non-leaning Independents reveal an increased susceptibility to implicitly endorse bi-partisan directed conspiracy theories when compared to leaners. (2) Republican-leaners demonstrate a stronger susceptibility to endorse right-wing aligned conspiracy theories (against Barack Obama), similar to Republican partisans. (3) Democrat-leaners, unlike Democrat partisans, do not demonstrate any particular susceptibility to implicitly endorse either right/left-wing aligned conspiracy theories (against Barack Obama or George W. Bush). Drawing from major theories from social, political, and cognitive psychology will contribute to an understanding of these phenomena. Concluding remarks include study limitations and future directions.
ContributorsJohnson, Chelsea (Author) / Duran, Nicholas D (Thesis advisor) / Robles-Sotelo, Elias (Committee member) / Hall, Deborah (Committee member) / Arizona State University (Publisher)
Created2017
Description
The Arizona Interfaith Alliance for Worker Justice (AIAWJ) was a mediating structure for those who wanted to be civically engaged in the labor movement and other coalitions in Phoenix, Arizona. It not only served its constituents, but it integrated, educated, and empowered them. Due to lack of funding the AIAWJ closed in the summer of 2016. Many community members from marginalized neighborhoods, other concerned citizens, students, myself, and others participated in their first and only civic engagement opportunities through this organization and were subsequently left with no connections, a barrier to being civically engaged. Through interviews and secondary data research, the relationship between people, mediating structures, and civic engagement activity are examined. The key findings support existing research that emphasizes the importance of mediating structures when it comes to civic engagement.
ContributorsSickler, Shawn (Author) / Luna, Ilana (Thesis advisor) / Hager, Mark (Committee member) / Keahey, Jennifer (Committee member) / Arizona State University (Publisher)
Created2016