Matching Items (5)
Filtering by
- All Subjects: Affect
- All Subjects: artificial intelligence
- Status: Published
Description
The present study examined daily survey data collected from married couples over the course roughly 14 days. I investigated the relationships of the morning quality ratings of three distinct spousal interactions conversation (physical affection, and sexual activity) reported in mornings on later-day positive and negative affect, as well as next-day intensity of negative somatic symptoms (e.g. headaches, dizziness, aches and pains). Hierarchical linear modeling was used to estimate path models for both husbands and wives. Direct and indirect effects were observed. Results showed that quality of conversation and physical affection increased later-day positive mood for both husbands and wives; however, positive quality activity increased later-day positive affect for wives only. Quality of sexual activity decreased later-day negative affect for wives only. Less later-day negative affect decreased next-day intensity of symptoms for both husbands and wives. Lastly, quality of sexual activity decreased later-day negative affect, which decreased next-day somatic symptoms for wives. This was the only significant indirect effect. Implications are that high marital quality is important for maintaining psychological health for both spouses, and physical health, particularly for wives.
ContributorsVincelette, Tara (Author) / Burleson, Mary H (Thesis advisor) / Roberts, Nicole A. (Committee member) / Schweitzer, Nicholas J (Committee member) / Arizona State University (Publisher)
Created2012
Description
Background: When studying how humans regulate their affect, it is important to recognize that affect regulation does not occur in a vacuum. As humans are an inherently social species, affect plays a crucial evolutionary role in social behavior, and social behavior likewise assumes an important role in affect and affect regulation. Emotion researchers are increasingly interested the specific ways people help to regulate and dysregulate one another’s affect, though experimental examinations of the extant models and theory are relatively few. This thesis presents a broad theoretical framework for social affect regulation between close others, considering the role of attachment theory and its developmental foundations for social affect regulation in adulthood. Affectionate and responsive touch is considered a major mechanism of regulatory benefit between people, both developmentally and in adulthood, and is the focus of the present investigation. Method: A total sample of 231 heterosexual married couples were recruited from the community. Participants were assigned to engage in affectionate touch or sit quietly, and/or engage in positive conversation prior to a stress task. Physiological data was collected continuously across the experiment. Hypotheses: Phasic respiratory sinus arrhythmia (RSA) was used to index the degree of regulatory engagement during the stressor for those who did and did not touch. It was hypothesized that touch would reduce stress appraisal and thus the need for regulatory engagement. This effect was predicted to be greater for those more anxiously attached while increasing the need for regulatory engagement in those more avoidantly attached. Secondarily, partner effects of attachment on sympathetic activation via pre-ejection period (PEP) change were tested. It was predicted that both attachment dimensions would predict a decrease in partner PEP change in the touch condition, with avoidant attachment having the strongest effect. Results: Hierarchical linear modeling techniques were used to account for nonindependence in dyadic observations. The first set of hypotheses were not supported, while the second set were partially supported. Wives’ avoidance significantly predicted husbands’ PEP change, but in the positive direction. This effect also significantly increased in the touch condition. Theoretical considerations and limitations are discussed.
ContributorsParkhurst, David Kevin (Author) / Burleson, Mary H (Thesis advisor) / Roberts, Nicole A. (Committee member) / Mickelson, Kristin D (Committee member) / Arizona State University (Publisher)
Created2017
Description
Affective computing allows computers to monitor and influence people’s affects, in other words emotions. Currently, there is a lot of research exploring what can be done with this technology. There are many fields, such as education, healthcare, and marketing, that this technology can transform. However, it is important to question what should be done. There are unique ethical considerations in regards to affective computing that haven't been explored. The purpose of this study is to understand the user’s perspective of affective computing in regards to the Association of Computing Machinery (ACM) Code of Ethics, to ultimately start developing a better understanding of these ethical concerns. For this study, participants were required to watch three different videos and answer a questionnaire, all while wearing an Emotiv EPOC+ EEG headset that measures their emotions. Using the information gathered, the study explores the ethics of affective computing through the user’s perspective.
ContributorsInjejikian, Angelica (Author) / Gonzalez-Sanchez, Javier (Thesis director) / Chavez-Echeagaray, Maria Elena (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
In the age of information, collecting and processing large amounts of data is an integral part of running a business. From training artificial intelligence to driving decision making, the applications of data are far-reaching. However, it is difficult to process many types of data; namely, unstructured data. Unstructured data is “information that either does not have a predefined data model or is not organized in a pre-defined manner” (Balducci & Marinova 2018). Such data are difficult to put into spreadsheets and relational databases due to their lack of numeric values and often come in the form of text fields written by the consumers (Wolff, R. 2020). The goal of this project is to help in the development of a machine learning model to aid CommonSpirit Health and ServiceNow, hence why this approach using unstructured data was selected. This paper provides a general overview of the process of unstructured data management and explores some existing implementations and their efficacy. It will then discuss our approach to converting unstructured cases into usable data that were used to develop an artificial intelligence model which is estimated to be worth $400,000 and save CommonSpirit Health $1,200,000 in organizational impact.
ContributorsBergsagel, Matteo (Author) / De Waard, Jan (Co-author) / Chavez-Echeagaray, Maria Elena (Thesis director) / Burns, Christopher (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-05
Description
Currently, recommender systems are used extensively to find the right audience with the "right" content over various platforms. Recommendations generated by these systems aim to offer relevant items to users. Different approaches have been suggested to solve this problem mainly by using the rating history of the user or by identifying the preferences of similar users. Most of the existing recommendation systems are formulated in an identical fashion, where a model is trained to capture the underlying preferences of users over different kinds of items. Once it is deployed, the model suggests personalized recommendations precisely, and it is assumed that the preferences of users are perfectly reflected by the historical data. However, such user data might be limited in practice, and the characteristics of users may constantly evolve during their intensive interaction between recommendation systems.
Moreover, most of these recommender systems suffer from the cold-start problems where insufficient data for new users or products results in reduced overall recommendation output. In the current study, we have built a recommender system to recommend movies to users. Biclustering algorithm is used to cluster the users and movies simultaneously at the beginning to generate explainable recommendations, and these biclusters are used to form a gridworld where Q-Learning is used to learn the policy to traverse through the grid. The reward function uses the Jaccard Index, which is a measure of common users between two biclusters. Demographic details of new users are used to generate recommendations that solve the cold-start problem too.
Lastly, the implemented algorithm is examined with a real-world dataset against the widely used recommendation algorithm and the performance for the cold-start cases.
Moreover, most of these recommender systems suffer from the cold-start problems where insufficient data for new users or products results in reduced overall recommendation output. In the current study, we have built a recommender system to recommend movies to users. Biclustering algorithm is used to cluster the users and movies simultaneously at the beginning to generate explainable recommendations, and these biclusters are used to form a gridworld where Q-Learning is used to learn the policy to traverse through the grid. The reward function uses the Jaccard Index, which is a measure of common users between two biclusters. Demographic details of new users are used to generate recommendations that solve the cold-start problem too.
Lastly, the implemented algorithm is examined with a real-world dataset against the widely used recommendation algorithm and the performance for the cold-start cases.
ContributorsSargar, Rushikesh Bapu (Author) / Atkinson, Robert K (Thesis advisor) / Chen, Yinong (Thesis advisor) / Chavez-Echeagaray, Maria Elena (Committee member) / Arizona State University (Publisher)
Created2020