Theses and Dissertations
This collection includes both ASU Theses and Dissertations, submitted by graduate students, and the Barrett, Honors College theses submitted by undergraduate students.
Displaying 1 - 2 of 2
Filtering by
- All Subjects: Educational technology
Description
With advances in automatic speech recognition, spoken dialogue systems are assuming increasingly social roles. There is a growing need for these systems to be socially responsive, capable of building rapport with users. In human-human interactions, rapport is critical to patient-doctor communication, conflict resolution, educational interactions, and social engagement. Rapport between people promotes successful collaboration, motivation, and task success. Dialogue systems which can build rapport with their user may produce similar effects, personalizing interactions to create better outcomes.
This dissertation focuses on how dialogue systems can build rapport utilizing acoustic-prosodic entrainment. Acoustic-prosodic entrainment occurs when individuals adapt their acoustic-prosodic features of speech, such as tone of voice or loudness, to one another over the course of a conversation. Correlated with liking and task success, a dialogue system which entrains may enhance rapport. Entrainment, however, is very challenging to model. People entrain on different features in many ways and how to design entrainment to build rapport is unclear. The first goal of this dissertation is to explore how acoustic-prosodic entrainment can be modeled to build rapport.
Towards this goal, this work presents a series of studies comparing, evaluating, and iterating on the design of entrainment, motivated and informed by human-human dialogue. These models of entrainment are implemented in the dialogue system of a robotic learning companion. Learning companions are educational agents that engage students socially to increase motivation and facilitate learning. As a learning companion’s ability to be socially responsive increases, so do vital learning outcomes. A second goal of this dissertation is to explore the effects of entrainment on concrete outcomes such as learning in interactions with robotic learning companions.
This dissertation results in contributions both technical and theoretical. Technical contributions include a robust and modular dialogue system capable of producing prosodic entrainment and other socially-responsive behavior. One of the first systems of its kind, the results demonstrate that an entraining, social learning companion can positively build rapport and increase learning. This dissertation provides support for exploring phenomena like entrainment to enhance factors such as rapport and learning and provides a platform with which to explore these phenomena in future work.
This dissertation focuses on how dialogue systems can build rapport utilizing acoustic-prosodic entrainment. Acoustic-prosodic entrainment occurs when individuals adapt their acoustic-prosodic features of speech, such as tone of voice or loudness, to one another over the course of a conversation. Correlated with liking and task success, a dialogue system which entrains may enhance rapport. Entrainment, however, is very challenging to model. People entrain on different features in many ways and how to design entrainment to build rapport is unclear. The first goal of this dissertation is to explore how acoustic-prosodic entrainment can be modeled to build rapport.
Towards this goal, this work presents a series of studies comparing, evaluating, and iterating on the design of entrainment, motivated and informed by human-human dialogue. These models of entrainment are implemented in the dialogue system of a robotic learning companion. Learning companions are educational agents that engage students socially to increase motivation and facilitate learning. As a learning companion’s ability to be socially responsive increases, so do vital learning outcomes. A second goal of this dissertation is to explore the effects of entrainment on concrete outcomes such as learning in interactions with robotic learning companions.
This dissertation results in contributions both technical and theoretical. Technical contributions include a robust and modular dialogue system capable of producing prosodic entrainment and other socially-responsive behavior. One of the first systems of its kind, the results demonstrate that an entraining, social learning companion can positively build rapport and increase learning. This dissertation provides support for exploring phenomena like entrainment to enhance factors such as rapport and learning and provides a platform with which to explore these phenomena in future work.
ContributorsLubold, Nichola Anne (Author) / Walker, Erin (Thesis advisor) / Pon-Barry, Heather (Thesis advisor) / Litman, Diane (Committee member) / VanLehn, Kurt (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2018
Description
This study examines the effects of providing persuasive writing and reading comprehension strategy training on source-based essay writing. Strategy training was administered through the use of the Writing Pal and the Interactive Strategy Trainer for Active Reading and Thinking (iSTART). The impact of both individual (writing or reading) and blended strategy training on source-based writing was investigated. A total of 261 participants completed the study; after removing incomplete and second language participants the source-based writing and system performance was assessed for 175 participants (n no instruction = 48, n iSTART =41, n Writing Pal =41, n blended =45).
Results indicated that participants who received blended strategy training produced higher quality source-based essays than participants who received only reading comprehension, writing strategy training, or no training. Furthermore, participants who received only reading comprehension or writing strategy training did not produce higher quality source-based essays than participants in the no-training control group. Time on task was investigated as a potential explanation for the results. Neither total time on task nor practice time were predictive of group differences on source-based essay scores. Analyses further suggested that the impact of strategy training does not differ as a function of prior abilities; however, training does seem to impact the relation between prior abilities and source-based essay scores. Specifically, prior writing ability was unrelated to performance for those who received writing training (i.e., Writing Pal and blended conditions), and prior reading ability was unrelated to performance for those received the full dosage of iSTART training. Overall, the findings suggest that when taught in conjunction with one another, reading comprehension and writing strategy training transfers to source-based writing, providing a positive impact on score. Potential changes to the Writing Pal and iSTART to more closely align training with source-based writing are discussed as methods of further increasing the impact of training on source-based writing.
Results indicated that participants who received blended strategy training produced higher quality source-based essays than participants who received only reading comprehension, writing strategy training, or no training. Furthermore, participants who received only reading comprehension or writing strategy training did not produce higher quality source-based essays than participants in the no-training control group. Time on task was investigated as a potential explanation for the results. Neither total time on task nor practice time were predictive of group differences on source-based essay scores. Analyses further suggested that the impact of strategy training does not differ as a function of prior abilities; however, training does seem to impact the relation between prior abilities and source-based essay scores. Specifically, prior writing ability was unrelated to performance for those who received writing training (i.e., Writing Pal and blended conditions), and prior reading ability was unrelated to performance for those received the full dosage of iSTART training. Overall, the findings suggest that when taught in conjunction with one another, reading comprehension and writing strategy training transfers to source-based writing, providing a positive impact on score. Potential changes to the Writing Pal and iSTART to more closely align training with source-based writing are discussed as methods of further increasing the impact of training on source-based writing.
ContributorsWeston Jennifer L (Author) / McNamara, Danielle S. (Thesis advisor) / Connor, Carol M (Committee member) / Glenberg, Arthur M. (Committee member) / Graham, Steve (Committee member) / Arizona State University (Publisher)
Created2015