ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 1 - 10 of 93
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
In October, 2009, participants of the Arizona Special Supplemental Nutrition Program for Women, Infants and Children (WIC) began receiving monthly Cash Value Vouchers (CVV) worth between six and 10 dollars towards the purchase of fresh fruits and vegetables. Data from the Arizona Department of Health Services (ADHS) showed CVV redemption rates in the first two years of the program were lower than the national average of 77% redemption. In response, the ADHS WIC Food List was expanded to also include canned and frozen fruits and vegetables. More recent data from ADHS suggest that redemption rates are improving, but variably exist among different WIC sub-populations. The purpose of this project was to identify themes related to the ease or difficulty of WIC CVV use amongst different categories of low-redeeming WIC participants. A total of 8 focus groups were conducted, four at a clinic in each of two Valley cities: Surprise and Mesa. Each of the four focus groups comprised one of four targeted WIC participant categories: pregnant, postpartum, breastfeeding, and children with participation ranging from 3-9 participants per group. Using the general inductive approach, recordings of the focus groups were transcribed, hand-coded and uploaded into qualitative analysis software resulting in four emergent themes including: interactions and shopping strategies, maximizing WIC value, redemption issues, and effect of rule change. Researchers identified twelve different subthemes related to the emergent theme of interactions and strategies to improve their experience, including economic considerations during redemption. Barriers related to interactions existed that made their purchase difficult, most notably anger from the cashier and other shoppers. However, participants made use of a number of strategies to facilitate WIC purchases or extract more value out of WIC benefits, such as pooling their CVV. Finally, it appears that the fruit and vegetable rule change was well received by those who were aware of the change. These data suggest a number of important avenues for future research, including verifying these themes are important within a larger, representative sample of Arizona WIC participants, and exploring strategies to minimize barriers identified by participants, such as use of electronic benefits transfer-style cards (EBT).
ContributorsBertmann, Farryl M. W (Author) / Wharton, Christopher (Christopher Mack), 1977- (Thesis advisor) / Ohri-Vachaspati, Punam (Committee member) / Johnston, Carol (Committee member) / Hampl, Jeffrey (Committee member) / Dixit-Joshi, Sujata (Committee member) / Barroso, Cristina (Committee member) / Arizona State University (Publisher)
Created2013
Description
Automating aspects of biocuration through biomedical information extraction could significantly impact biomedical research by enabling greater biocuration throughput and improving the feasibility of a wider scope. An important step in biomedical information extraction systems is named entity recognition (NER), where mentions of entities such as proteins and diseases are located within natural-language text and their semantic type is determined. This step is critical for later tasks in an information extraction pipeline, including normalization and relationship extraction. BANNER is a benchmark biomedical NER system using linear-chain conditional random fields and the rich feature set approach. A case study with BANNER locating genes and proteins in biomedical literature is described. The first corpus for disease NER adequate for use as training data is introduced, and employed in a case study of disease NER. The first corpus locating adverse drug reactions (ADRs) in user posts to a health-related social website is also described, and a system to locate and identify ADRs in social media text is created and evaluated. The rich feature set approach to creating NER feature sets is argued to be subject to diminishing returns, implying that additional improvements may require more sophisticated methods for creating the feature set. This motivates the first application of multivariate feature selection with filters and false discovery rate analysis to biomedical NER, resulting in a feature set at least 3 orders of magnitude smaller than the set created by the rich feature set approach. Finally, two novel approaches to NER by modeling the semantics of token sequences are introduced. The first method focuses on the sequence content by using language models to determine whether a sequence resembles entries in a lexicon of entity names or text from an unlabeled corpus more closely. The second method models the distributional semantics of token sequences, determining the similarity between a potential mention and the token sequences from the training data by analyzing the contexts where each sequence appears in a large unlabeled corpus. The second method is shown to improve the performance of BANNER on multiple data sets.
ContributorsLeaman, James Robert (Author) / Gonzalez, Graciela (Thesis advisor) / Baral, Chitta (Thesis advisor) / Cohen, Kevin B (Committee member) / Liu, Huan (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
There are several visual dimensions of food that can affect food intake, example portion size, color, and variety. This dissertation elucidates the effect of number of pieces of food on preference and amount of food consumed in humans and motivation for food in animals. Chapter 2 Experiment 1 showed that rats preferred and also ran faster for multiple pieces (30, 10 mg pellets) than an equicaloric, single piece of food (300 mg) showing that multiple pieces of food are more rewarding than a single piece. Chapter 2 Experiment 2 showed that rats preferred a 30-pellet food portion clustered together rather than scattered. Preference and motivation for clustered food pieces may be interpreted based on the optimal foraging theory that animals prefer foods that can maximize energy gain and minimize the risk of predation. Chapter 3 Experiment 1 showed that college students preferred and ate less of a multiple-piece than a single-piece portion and also ate less in a test meal following the multiple-piece than single-piece portion. Chapter 3 Experiment 2 replicated the results in Experiment 1 and used a bagel instead of chicken. Chapter 4 showed that college students given a five-piece chicken portion scattered on a plate ate less in a meal and in a subsequent test meal than those given the same portion clustered together. This is consistent with the hypothesis that multiple pieces of food may appear like more food because they take up a larger surface area than a single-piece portion. All together, these studies show that number and surface area occupied by food pieces are important visual cues determining food choice in animals and both food choice and intake in humans.
ContributorsBajaj, Devina (Author) / Phillips, Elizabeth D. (Thesis advisor) / Cohen, Adam (Committee member) / Johnston, Carol (Committee member) / Bimonte-Nelson, Heather A. (Committee member) / Arizona State University (Publisher)
Created2013
Description
Data mining is increasing in importance in solving a variety of industry problems. Our initiative involves the estimation of resource requirements by skill set for future projects by mining and analyzing actual resource consumption data from past projects in the semiconductor industry. To achieve this goal we face difficulties like data with relevant consumption information but stored in different format and insufficient data about project attributes to interpret consumption data. Our first goal is to clean the historical data and organize it into meaningful structures for analysis. Once the preprocessing on data is completed, different data mining techniques like clustering is applied to find projects which involve resources of similar skillsets and which involve similar complexities and size. This results in "resource utilization templates" for groups of related projects from a resource consumption perspective. Then project characteristics are identified which generate this diversity in headcounts and skillsets. These characteristics are not currently contained in the data base and are elicited from the managers of historical projects. This represents an opportunity to improve the usefulness of the data collection system for the future. The ultimate goal is to match the product technical features with the resource requirement for projects in the past as a model to forecast resource requirements by skill set for future projects. The forecasting model is developed using linear regression with cross validation of the training data as the past project execution are relatively few in number. Acceptable levels of forecast accuracy are achieved relative to human experts' results and the tool is applied to forecast some future projects' resource demand.
ContributorsBhattacharya, Indrani (Author) / Sen, Arunabha (Thesis advisor) / Kempf, Karl G. (Thesis advisor) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Health knowledge alone does not appear to lead to sustained healthy behavior, suggesting the need for alternative methods for improving diet. Recent research shows a possible role of moral contexts of food production on diet related behaviors; however no studies have been conducted to specifically explore the relationship between moral constructs and food consumption. This study examined the relationship between fast food consumption and two measures of morality, Moral Foundations Questionnaire (MFQ), specifically harm/care and purity/sanctity foundations, and the Ethical Concern in food choice (EC) questionnaire, which includes animal welfare, environment protection, political values, and religion subscales. The study also examined the association between the measures of morality. 739 participants, primarily female (71.4%) and non-Hispanic Whites (76.5%), completed an online survey that included the MFQ, the EC questionnaire, and a brief fast food screener. Participant's morality scores in relation to their fast food consumption were examined first using bivariate ANOVA analysis and then using logistic regression to control for covariates. The MFQ foundations were compared with the EC subscales using Pearson correlation coefficient. Significant bivariate relationships were seen between fast food consumption and the MFQ's purity/sanctity foundation and EC's religion subscales (p<0.05). However these significant bivariate relationships did not hold after controlling for gender, race, university education, and religion in the logistic regression analysis. The foundations of the MFQ were positively correlated with the subscales for the EC questionnaire (r values ranging from .233-.613 (p<0.01). MFQ's purity/sanctity foundation and EC's religion subscale were the two most highly correlated (r=.613, p<0.01) showing that moral intuitions may be associated with eating decision making. The study did not find significant associations between MFQ or EC scores and fast food consumption.
ContributorsMartinelli, Sarah (Author) / Ohri-Vachaspati, Punam (Thesis advisor) / Hekler, Eric B. (Committee member) / Wharton, Christopher (Christopher Mack), 1977- (Committee member) / Johnston, Carol (Committee member) / Arizona State University (Publisher)
Created2013
Description
Background: Previous research suggests a healthy eater schema (i.e., identifying yourself as a healthy eater) may be a useful concept to target in interventions. A "stealth" intervention that discussed the moral issues related to food worked better at promoting healthful eating than an intervention focused on the health benefits. No research has explored the relationship between moral foundations, a theoretical model focused on delineating core "foundations" for making a moral decision, and healthy eater self-identity or self-efficacy. Purpose: We explored the relationship between moral foundations (i.e., harm/care, fairness/reciprocity, in-group/loyalty, authority/respect, & purity/sanctity) and health eater self-identity and fruit and vegetable self-efficacy (FVSE). Methods: 542 participants completed an online cross-sectional survey, which included moral foundations (i.e., MFQ), political views, healthy eater self-identity (i.e., HESS), and FVSE measures. Logistic regression was used to assess the relationship between moral foundations between healthy eater self-identity after controlling for age, gender, major, BMI, and political beliefs. OLS regression was used to explore the relationship between self-efficacy and the moral foundations after controlling for the covariates. Results: 75.6% of the sample were college students, with a mean age of 25.27 (SD=8.61). 25.1% of students were nutrition majors. Harm/care, authority/respect, and ingroup/loyalty were significantly associated with healthy eater schema, (i.e., OR=1.7, p<.001, OR=1.5, p=.009, and OR=1.4, p=.027, respectively). Ingroup/loyalty, authority/respect, and purity/sanctity were related to FVSE (p=.006, p=.002, p=.04, respectively). Conclusion: Among college students, harm/care and authority/respect were associated with a healthy eater schema. Future research should explore possible uses of these moral foundations in interventions (e.g., a plant-based diet based on reduced harm to animals or eating fewer processed views based on "traditional" values).
ContributorsKiser, Sarah (Author) / Hekler, Eric B. (Thesis advisor) / Ohri-Vachaspati, Punam (Committee member) / Wharton, Christopher (Christopher Mack), 1977- (Committee member) / Johnston, Carol (Committee member) / Arizona State University (Publisher)
Created2013
Description
Contemporary online social platforms present individuals with social signals in the form of news feed on their peers' activities. On networks such as Facebook, Quora, network operator decides how that information is shown to an individual. Then the user, with her own interests and resource constraints selectively acts on a subset of items presented to her. The network operator again, shows that activity to a selection of peers, and thus creating a behavioral loop. That mechanism of interaction and information flow raises some very interesting questions such as: can network operator design social signals to promote a particular activity like sustainability, public health care awareness, or to promote a specific product? The focus of my thesis is to answer that question. In this thesis, I develop a framework to personalize social signals for users to guide their activities on an online platform. As the result, we gradually nudge the activity distribution on the platform from the initial distribution p to the target distribution q. My work is particularly applicable to guiding collaborations, guiding collective actions, and online advertising. In particular, I first propose a probabilistic model on how users behave and how information flows on the platform. The main part of this thesis after that discusses the Influence Individuals through Social Signals (IISS) framework. IISS consists of four main components: (1) Learner: it learns users' interests and characteristics from their historical activities using Bayesian model, (2) Calculator: it uses gradient descent method to compute the intermediate activity distributions, (3) Selector: it selects users who can be influenced to adopt or drop specific activities, (4) Designer: it personalizes social signals for each user. I evaluate the performance of IISS framework by simulation on several network topologies such as preferential attachment, small world, and random. I show that the framework gradually nudges users' activities to approach the target distribution. I use both simulation and mathematical method to analyse convergence properties such as how fast and how close we can approach the target distribution. When the number of activities is 3, I show that for about 45% of target distributions, we can achieve KL-divergence as low as 0.05. But for some other distributions KL-divergence can be as large as 0.5.
ContributorsLe, Tien D (Author) / Sundaram, Hari (Thesis advisor) / Davulcu, Hasan (Thesis advisor) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2014
Description
Most data cleaning systems aim to go from a given deterministic dirty database to another deterministic but clean database. Such an enterprise pre–supposes that it is in fact possible for the cleaning process to uniquely recover the clean versions of each dirty data tuple. This is not possible in many cases, where the most a cleaning system can do is to generate a (hopefully small) set of clean candidates for each dirty tuple. When the cleaning system is required to output a deterministic database, it is forced to pick one clean candidate (say the "most likely" candidate) per tuple. Such an approach can lead to loss of information. For example, consider a situation where there are three equally likely clean candidates of a dirty tuple. An appealing alternative that avoids such an information loss is to abandon the requirement that the output database be deterministic. In other words, even though the input (dirty) database is deterministic, I allow the reconstructed database to be probabilistic. Although such an approach does avoid the information loss, it also brings forth several challenges. For example, how many alternatives should be kept per tuple in the reconstructed database? Maintaining too many alternatives increases the size of the reconstructed database, and hence the query processing time. Second, while processing queries on the probabilistic database may well increase recall, how would they affect the precision of the query processing? In this thesis, I investigate these questions. My investigation is done in the context of a data cleaning system called BayesWipe that has the capability of producing multiple clean candidates per each dirty tuple, along with the probability that they are the correct cleaned version. I represent these alternatives as tuples in a tuple disjoint probabilistic database, and use the Mystiq system to process queries on it. This probabilistic reconstruction (called BayesWipe–PDB) is compared to a deterministic reconstruction (called BayesWipe–DET)—where the most likely clean candidate for each tuple is chosen, and the rest of the alternatives discarded.
ContributorsRihan, Preet Inder Singh (Author) / Kambhampati, Subbarao (Thesis advisor) / Liu, Huan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2013
Description
As the size and scope of valuable datasets has exploded across many industries and fields of research in recent years, an increasingly diverse audience has sought out effective tools for their large-scale data analytics needs. Over this period, machine learning researchers have also been very prolific in designing improved algorithms which are capable of finding the hidden structure within these datasets. As consumers of popular Big Data frameworks have sought to apply and benefit from these improved learning algorithms, the problems encountered with the frameworks have motivated a new generation of Big Data tools to address the shortcomings of the previous generation. One important example of this is the improved performance in the newer tools with the large class of machine learning algorithms which are highly iterative in nature. In this thesis project, I set about to implement a low-rank matrix completion algorithm (as an example of a highly iterative algorithm) within a popular Big Data framework, and to evaluate its performance processing the Netflix Prize dataset. I begin by describing several approaches which I attempted, but which did not perform adequately. These include an implementation of the Singular Value Thresholding (SVT) algorithm within the Apache Mahout framework, which runs on top of the Apache Hadoop MapReduce engine. I then describe an approach which uses the Divide-Factor-Combine (DFC) algorithmic framework to parallelize the state-of-the-art low-rank completion algorithm Orthogoal Rank-One Matrix Pursuit (OR1MP) within the Apache Spark engine. I describe the results of a series of tests running this implementation with the Netflix dataset on clusters of various sizes, with various degrees of parallelism. For these experiments, I utilized the Amazon Elastic Compute Cloud (EC2) web service. In the final analysis, I conclude that the Spark DFC + OR1MP implementation does indeed produce competitive results, in both accuracy and performance. In particular, the Spark implementation performs nearly as well as the MATLAB implementation of OR1MP without any parallelism, and improves performance to a significant degree as the parallelism increases. In addition, the experience demonstrates how Spark's flexible programming model makes it straightforward to implement this parallel and iterative machine learning algorithm.
ContributorsKrouse, Brian (Author) / Ye, Jieping (Thesis advisor) / Liu, Huan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2014