Master of Science / Department of Computing and Information Sciences / Daniel Andresen / FNPRS program offers nutrition education all over the counties in Kansas. It is necessary to keep track of the budget expenses for the program, resources used and many other parameters involved in the program. There exist number of commodities and products in the process of educating people. Research is needed to determine which value-added products or processes are economically possible and what percentage of it is accepted by people. For these issues, it is very important to maintain this information in a database and generate reports accordingly. The aim of the project is to create a web interface for users to enter the program information regarding the various programs conducted by Family Nutrition Program. The various kinds of data include information about the budget for the program, information about the various collaborating agencies, various kinds of resources used, services provided, proposed equipment and travel funds etc. Users for this application are county agents who take the responsibility of conducting the program and managing their data. Creating a web interface provides a solution to facilitate the agents to manage their data more efficiently and to monitor their records on a day to day basis. It also aims for generating reports for Family Nutrition Program in order to keep a check over their advancements in the program. This project involves handling of various kinds of information such as FNP Proposals, Agent information, FNP Funds, Collaborating Agencies. Database maintenance is made simple thereby allowing the administrators to add as much as data possible and manage accordingly.

Doctor of Philosophy / Department of Psychological Sciences / Laura A. Brannon / Two common types of advertisement avoidance behaviors in digital domains are skipping and zipping. Skipping involves pressing a “skip ad” button when viewing television content online, and zipping involves pressing a fast-forward button when viewing the same content through some type of recording device (e.g. Digital Video Recording device). The purpose of these studies was to examine if specific factors regarding the content of the advertisement, the persuasion context, and characteristics of the viewer reduce occurrences of skipping and zipping behavior. Participants in these two studies saw a combination of television shows and advertisements. One target advertisement marketed a fictional MP3 player while another discussed the dangers of binge drinking. One version each of the MP3 and binge drinking advertisements contained average-looking (i.e. normal) actors, and the other half contained above-average-looking (i.e. attractive) actors. Half of the viewers were allowed to choose which type of advertisements they would watch while the other half were forced to watch a particular type. The results of one study showed that participants were more likely to skip the MP3 advertisement than the binge drinking advertisement after making an advertisement choice when both contained normally attractive actors. These findings demonstrate that the effect of advertisement choice may be more complicated than previously found. Instead of acting as a means to improve avoidance rates, advertisement choice may make the content more salient to participants. Thus, viewers’ perceptions of the advertisement after making an advertisement choice may determine whether avoidance occurs.

Master of Science / Department of Computing and Information Sciences / Doina Caragea / As the web pages continuously change and their number grows exponentially, the need for genre classification of web pages also increases. One simple reason for this is given by the need to group web pages into various genre categories in order to reduce the complexities of various web tasks (e.g., search). Experts unanimously agree on the huge potential of genre classification of web pages. However, while everybody agrees that genre classification of web pages is necessary, researchers face problems in finding enough labeled data to perform supervised classification of web pages into various genres. The high cost of skilled manual labor, rapid changing nature of web and never ending growth of web pages are the main reasons for the limited amount of labeled data. On the contrary unlabeled data can be acquired relatively inexpensively in comparison to labeled data. This suggests the use of semi-supervised learning approaches for genre classification, instead of using supervised approaches. Semi-supervised learning makes use of both labeled and unlabeled data for training - typically a small amount of labeled data and a large amount of unlabeled data. Semi-supervised learning have been extensively used in text classification problems. Given the link structure of the web, for web-page classification one can use link features in addition to the content features that are used for general text classification. Hence, the feature set corresponding to web-pages can be easily divided into two views, namely content and link based feature views. Intuitively, the two feature views are conditionally independent given the genre category and have the ability to predict the class on their own. The scarcity of labeled data, availability of large amounts of unlabeled data, richer set of features as compared to the conventional text classification tasks (specifically complementary and sufficient views of features) have encouraged us to use co-training as a tool to perform semi-supervised learning. During co-training labeled examples represented using the two views are used to learn distinct classifiers, which keep improving at each iteration by sharing the most confident predictions on the unlabeled data. In this work, we classify web-pages of .eu domain consisting of 1232 labeled host and 20000 unlabeled hosts (provided by the European Archive Foundation [Benczur et al., 2010]) into six different genres, using co-training. We compare our results with the results produced by standard supervised methods. We find that co-training can be an effective and cheap alternative to costly supervised learning. This is mainly due to the two independent and complementary feature sets of web: content based features and link based features.