Learning Data-Driven Models of Non-Verbal Behaviors for Building Rapport Using an Intelligent Virtual Agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness. Evidence-based patient-centered Brief Motivational Interviewing (BMI) interven- tions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary. Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems. To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].

Developing a Data-Driven Classification of South Florida Plant Communities

A comprehensive, broadly accepted vegetation classification is important for ecosystem management, particularly for planning and monitoring. South Florida vegetation classification systems that are currently in use were largely arrived at subjectively and intuitively with the involvement of experienced botanical observers and ecologists, but with little support in terms of quantitative field data. The need to develop a field data-driven classification of South Florida vegetation that builds on the ecological organization has been recognized by the National Park Service and vegetation practitioners in the region. The present work, funded by the National Park Service Inventory and Monitoring Program - South Florida/Caribbean Network (SFCN), covers the first stage of a larger project whose goal is to apply extant vegetation data to test, and revise as necessary, an existing, widely used classification (Rutchey et al. 2006). The objectives of the first phase of the project were (1) to identify useful existing datasets, (2) to collect these data and compile them into a geodatabase, (3) to conduct an initial classification analysis of marsh sites, and (4) to design a strategy for augmenting existing information from poorly represented landscapes in order to develop a more comprehensive south Florida classification.

Learning data-driven models of non-verbal behaviors for building rapport using an intelligent virtual agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness.^ Evidence-based patient-centered Brief Motivational Interviewing (BMI) interventions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary.^ Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems.^ To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].^

Principal component analysis and assessment of language network activation patterns in pediatric epilepsy

This dissertation establishes a novel data-driven method to identify language network activation patterns in pediatric epilepsy through the use of the Principal Component Analysis (PCA) on functional magnetic resonance imaging (fMRI). A total of 122 subjects’ data sets from five different hospitals were included in the study through a web-based repository site designed here at FIU. Research was conducted to evaluate different classification and clustering techniques in identifying hidden activation patterns and their associations with meaningful clinical variables. The results were assessed through agreement analysis with the conventional methods of lateralization index (LI) and visual rating. What is unique in this approach is the new mechanism designed for projecting language network patterns in the PCA-based decisional space. Synthetic activation maps were randomly generated from real data sets to uniquely establish nonlinear decision functions (NDF) which are then used to classify any new fMRI activation map into typical or atypical. The best nonlinear classifier was obtained on a 4D space with a complexity (nonlinearity) degree of 7. Based on the significant association of language dominance and intensities with the top eigenvectors of the PCA decisional space, a new algorithm was deployed to delineate primary cluster members without intensity normalization. In this case, three distinct activations patterns (groups) were identified (averaged kappa with rating 0.65, with LI 0.76) and were characterized by the regions of: (1) the left inferior frontal Gyrus (IFG) and left superior temporal gyrus (STG), considered typical for the language task; (2) the IFG, left mesial frontal lobe, right cerebellum regions, representing a variant left dominant pattern by higher activation; and (3) the right homologues of the first pattern in Broca's and Wernicke's language areas. Interestingly, group 2 was found to reflect a different language compensation mechanism than reorganization. Its high intensity activation suggests a possible remote effect on the right hemisphere focus on traditionally left-lateralized functions. In retrospect, this data-driven method provides new insights into mechanisms for brain compensation/reorganization and neural plasticity in pediatric epilepsy.

Monitoring Ecosystems: Interdisciplinary Approaches For Evaluating Ecoregional Initiatives

Monitoring Ecosystems brings together leading scientists and researchers to offer a ground-breaking synthesis of lessons learned about ecological monitoring in major ecoregional initiatives around the United States. Contributors present insights and experiences gained from their work in designing, developing, and implementing comprehensive ecosystem monitoring programs in the Pacific Northwest, the lower Colorado River Basin, and the Florida Everglades. The book: outlines the conceptual and scientific underpinnings for regional-scale ecosystem monitoring examines the role and importance of data management, modeling, and integrative analyses considers techniques for and experience with monitoring habitats, populations, and communities Chapters by the editors synthesize and expand on points made throughout the volume and present recommendations for establishing frameworks for monitoring across scales, from local to international. Monitoring Ecosystems presents a critical examination of the lessons learned from direct experience along with generalized conclusions that can be applied to monitoring programs in the United States and around the world. It is a vital contribution to science-based monitoring efforts that will allow those responsible for developing and implementing ecoregional initiatives to make use of knowledge gained in previous efforts.

Class Size Reduction: A Significant Option for Improving Student Learning

Raising academic standards is a driving force behind public school initiatives. True educational reform requires a data-driven approach to choosing valid options for student improvement. We discuss current and continuing research that provides evidence that class size reduction, with related variables, is a significant option for improving student learning.

Network construction and graph theoretical analysis of functional language networks in pediatric epilepsy

This dissertation introduces a new approach for assessing the effects of pediatric epilepsy on the language connectome. Two novel data-driven network construction approaches are presented. These methods rely on connecting different brain regions using either extent or intensity of language related activations as identified by independent component analysis of fMRI data. An auditory description decision task (ADDT) paradigm was used to activate the language network for 29 patients and 30 controls recruited from three major pediatric hospitals. Empirical evaluations illustrated that pediatric epilepsy can cause, or is associated with, a network efficiency reduction. Patients showed a propensity to inefficiently employ the whole brain network to perform the ADDT language task; on the contrary, controls seemed to efficiently use smaller segregated network components to achieve the same task. To explain the causes of the decreased efficiency, graph theoretical analysis was carried out. The analysis revealed no substantial global network feature differences between the patient and control groups. It also showed that for both subject groups the language network exhibited small-world characteristics; however, the patient's extent of activation network showed a tendency towards more random networks. It was also shown that the intensity of activation network displayed ipsilateral hub reorganization on the local level. The left hemispheric hubs displayed greater centrality values for patients, whereas the right hemispheric hubs displayed greater centrality values for controls. This hub hemispheric disparity was not correlated with a right atypical language laterality found in six patients. Finally it was shown that a multi-level unsupervised clustering scheme based on self-organizing maps, a type of artificial neural network, and k-means was able to fairly and blindly separate the subjects into their respective patient or control groups. The clustering was initiated using the local nodal centrality measurements only. Compared to the extent of activation network, the intensity of activation network clustering demonstrated better precision. This outcome supports the assertion that the local centrality differences presented by the intensity of activation network can be associated with focal epilepsy.^

Event mining for system and service management

Modern IT infrastructures are constructed by large scale computing systems and administered by IT service providers. Manually maintaining such large computing systems is costly and inefficient. Service providers often seek automatic or semi-automatic methodologies of detecting and resolving system issues to improve their service quality and efficiency. This dissertation investigates several data-driven approaches for assisting service providers in achieving this goal. The detailed problems studied by these approaches can be categorized into the three aspects in the service workflow: 1) preprocessing raw textual system logs to structural events; 2) refining monitoring configurations for eliminating false positives and false negatives; 3) improving the efficiency of system diagnosis on detected alerts. Solving these problems usually requires a huge amount of domain knowledge about the particular computing systems. The approaches investigated by this dissertation are developed based on event mining algorithms, which are able to automatically derive part of that knowledge from the historical system logs, events and tickets. ^ In particular, two textual clustering algorithms are developed for converting raw textual logs into system events. For refining the monitoring configuration, a rule based alert prediction algorithm is proposed for eliminating false alerts (false positives) without losing any real alert and a textual classification method is applied to identify the missing alerts (false negatives) from manual incident tickets. For system diagnosis, this dissertation presents an efficient algorithm for discovering the temporal dependencies between system events with corresponding time lags, which can help the administrators to determine the redundancies of deployed monitoring situations and dependencies of system components. To improve the efficiency of incident ticket resolving, several KNN-based algorithms that recommend relevant historical tickets with resolutions for incoming tickets are investigated. Finally, this dissertation offers a novel algorithm for searching similar textual event segments over large system logs that assists administrators to locate similar system behaviors in the logs. Extensive empirical evaluation on system logs, events and tickets from real IT infrastructures demonstrates the effectiveness and efficiency of the proposed approaches.^

Statistical dialog management for health interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. ^ Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. ^ The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. ^ In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.^

Temporal Mining for Distributed Systems

Many systems and applications are continuously producing events. These events are used to record the status of the system and trace the behaviors of the systems. By examining these events, system administrators can check the potential problems of these systems. If the temporal dynamics of the systems are further investigated, the underlying patterns can be discovered. The uncovered knowledge can be leveraged to predict the future system behaviors or to mitigate the potential risks of the systems. Moreover, the system administrators can utilize the temporal patterns to set up event management rules to make the system more intelligent. With the popularity of data mining techniques in recent years, these events grad- ually become more and more useful. Despite the recent advances of the data mining techniques, the application to system event mining is still in a rudimentary stage. Most of works are still focusing on episodes mining or frequent pattern discovering. These methods are unable to provide a brief yet comprehensible summary to reveal the valuable information from the high level perspective. Moreover, these methods provide little actionable knowledge to help the system administrators to better man- age the systems. To better make use of the recorded events, more practical techniques are required. From the perspective of data mining, three correlated directions are considered to be helpful for system management: (1) Provide concise yet comprehensive summaries about the running status of the systems; (2) Make the systems more intelligence and autonomous; (3) Effectively detect the abnormal behaviors of the systems. Due to the richness of the event logs, all these directions can be solved in the data-driven manner. And in this way, the robustness of the systems can be enhanced and the goal of autonomous management can be approached. This dissertation mainly focuses on the foregoing directions that leverage tem- poral mining techniques to facilitate system management. More specifically, three concrete topics will be discussed, including event, resource demand prediction, and streaming anomaly detection. Besides the theoretic contributions, the experimental evaluation will also be presented to demonstrate the effectiveness and efficacy of the corresponding solutions.

Principal Component Analysis and Assessment of Language Network Activation Patterns in Pediatric Epilepsy

This dissertation establishes a novel data-driven method to identify language network activation patterns in pediatric epilepsy through the use of the Principal Component Analysis (PCA) on functional magnetic resonance imaging (fMRI). A total of 122 subjects’ data sets from five different hospitals were included in the study through a web-based repository site designed here at FIU. Research was conducted to evaluate different classification and clustering techniques in identifying hidden activation patterns and their associations with meaningful clinical variables. The results were assessed through agreement analysis with the conventional methods of lateralization index (LI) and visual rating. What is unique in this approach is the new mechanism designed for projecting language network patterns in the PCA-based decisional space. Synthetic activation maps were randomly generated from real data sets to uniquely establish nonlinear decision functions (NDF) which are then used to classify any new fMRI activation map into typical or atypical. The best nonlinear classifier was obtained on a 4D space with a complexity (nonlinearity) degree of 7. Based on the significant association of language dominance and intensities with the top eigenvectors of the PCA decisional space, a new algorithm was deployed to delineate primary cluster members without intensity normalization. In this case, three distinct activations patterns (groups) were identified (averaged kappa with rating 0.65, with LI 0.76) and were characterized by the regions of: 1) the left inferior frontal Gyrus (IFG) and left superior temporal gyrus (STG), considered typical for the language task; 2) the IFG, left mesial frontal lobe, right cerebellum regions, representing a variant left dominant pattern by higher activation; and 3) the right homologues of the first pattern in Broca's and Wernicke's language areas. Interestingly, group 2 was found to reflect a different language compensation mechanism than reorganization. Its high intensity activation suggests a possible remote effect on the right hemisphere focus on traditionally left-lateralized functions. In retrospect, this data-driven method provides new insights into mechanisms for brain compensation/reorganization and neural plasticity in pediatric epilepsy.

Improved Criteria for Estimating Calibration Factors for Highway Safety Manual (HSM) Applications

The Highway Safety Manual (HSM) estimates roadway safety performance based on predictive models that were calibrated using national data. Calibration factors are then used to adjust these predictive models to local conditions for local applications. The HSM recommends that local calibration factors be estimated using 30 to 50 randomly selected sites that experienced at least a total of 100 crashes per year. It also recommends that the factors be updated every two to three years, preferably on an annual basis. However, these recommendations are primarily based on expert opinions rather than data-driven research findings. Furthermore, most agencies do not have data for many of the input variables recommended in the HSM. This dissertation is aimed at determining the best way to meet three major data needs affecting the estimation of calibration factors: (1) the required minimum sample sizes for different roadway facilities, (2) the required frequency for calibration factor updates, and (3) the influential variables affecting calibration factors. In this dissertation, statewide segment and intersection data were first collected for most of the HSM recommended calibration variables using a Google Maps application. In addition, eight years (2005-2012) of traffic and crash data were retrieved from existing databases from the Florida Department of Transportation. With these data, the effect of sample size criterion on calibration factor estimates was first studied using a sensitivity analysis. The results showed that the minimum sample sizes not only vary across different roadway facilities, but they are also significantly higher than those recommended in the HSM. In addition, results from paired sample t-tests showed that calibration factors in Florida need to be updated annually. To identify influential variables affecting the calibration factors for roadway segments, the variables were prioritized by combining the results from three different methods: negative binomial regression, random forests, and boosted regression trees. Only a few variables were found to explain most of the variation in the crash data. Traffic volume was consistently found to be the most influential. In addition, roadside object density, major and minor commercial driveway densities, and minor residential driveway density were also identified as influential variables.

Statistical Dialog Management for Health Interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.

A Retrospective-Longitudinal Examination of the Relationship between Apportionment of Seat Time in Community-College Algebra Courses and Student Academic Performance

During the past decade, there has been a dramatic increase by postsecondary institutions in providing academic programs and course offerings in a multitude of formats and venues (Biemiller, 2009; Kucsera & Zimmaro, 2010; Lang, 2009; Mangan, 2008). Strategies pertaining to reapportionment of course-delivery seat time have been a major facet of these institutional initiatives; most notably, within many open-door 2-year colleges. Often, these enrollment-management decisions are driven by the desire to increase market-share, optimize the usage of finite facility capacity, and contain costs, especially during these economically turbulent times. So, while enrollments have surged to the point where nearly one in three 18-to-24 year-old U.S. undergraduates are community college students (Pew Research Center, 2009), graduation rates, on average, still remain distressingly low (Complete College America, 2011). Among the learning-theory constructs related to seat-time reapportionment efforts is the cognitive phenomenon commonly referred to as the spacing effect, the degree to which learning is enhanced by a series of shorter, separated sessions as opposed to fewer, more massed episodes. This ex post facto study explored whether seat time in a postsecondary developmental-level algebra course is significantly related to: course success; course-enrollment persistence; and, longitudinally, the time to successfully complete a general-education-level mathematics course. Hierarchical logistic regression and discrete-time survival analysis were used to perform a multi-level, multivariable analysis of a student cohort (N = 3,284) enrolled at a large, multi-campus, urban community college. The subjects were retrospectively tracked over a 2-year longitudinal period. The study found that students in long seat-time classes tended to withdraw earlier and more often than did their peers in short seat-time classes (p < .05). Additionally, a model comprised of nine statistically significant covariates (all with p-values less than .01) was constructed. However, no longitudinal seat-time group differences were detected nor was there sufficient statistical evidence to conclude that seat time was predictive of developmental-level course success. A principal aim of this study was to demonstrate—to educational leaders, researchers, and institutional-research/business-intelligence professionals—the advantages and computational practicability of survival analysis, an underused but more powerful way to investigate changes in students over time.

Network Construction and Graph Theoretical Analysis of Functional Language Networks in Pediatric Epilepsy

This dissertation introduces a new approach for assessing the effects of pediatric epilepsy on the language connectome. Two novel data-driven network construction approaches are presented. These methods rely on connecting different brain regions using either extent or intensity of language related activations as identified by independent component analysis of fMRI data. An auditory description decision task (ADDT) paradigm was used to activate the language network for 29 patients and 30 controls recruited from three major pediatric hospitals. Empirical evaluations illustrated that pediatric epilepsy can cause, or is associated with, a network efficiency reduction. Patients showed a propensity to inefficiently employ the whole brain network to perform the ADDT language task; on the contrary, controls seemed to efficiently use smaller segregated network components to achieve the same task. To explain the causes of the decreased efficiency, graph theoretical analysis was carried out. The analysis revealed no substantial global network feature differences between the patient and control groups. It also showed that for both subject groups the language network exhibited small-world characteristics; however, the patient’s extent of activation network showed a tendency towards more random networks. It was also shown that the intensity of activation network displayed ipsilateral hub reorganization on the local level. The left hemispheric hubs displayed greater centrality values for patients, whereas the right hemispheric hubs displayed greater centrality values for controls. This hub hemispheric disparity was not correlated with a right atypical language laterality found in six patients. Finally it was shown that a multi-level unsupervised clustering scheme based on self-organizing maps, a type of artificial neural network, and k-means was able to fairly and blindly separate the subjects into their respective patient or control groups. The clustering was initiated using the local nodal centrality measurements only. Compared to the extent of activation network, the intensity of activation network clustering demonstrated better precision. This outcome supports the assertion that the local centrality differences presented by the intensity of activation network can be associated with focal epilepsy.