This study investigated the ability to relate a test taker’s non-verbal cues during online assessments to probable cheating incidents. Specifically, this study focused on the role of time delay, head pose and affective state for detection of cheating incidences in a lab-based online testing session. The analysis of a test taker’s non-verbal cues indicated that time delay, the variation of a student’s head pose relative to the computer screen and confusion had significantly statistical relation to cheating behaviors. Additionally, time delay, head pose relative to the computer screen, confusion, and the interaction term of confusion and time delay were predictors in a support vector machine of cheating prediction with an average accuracy of 70.7%. The current algorithm could automatically flag suspicious student behavior for proctors in large scale online courses during remotely administered exams.

Technological advances have enabled the generation and collection of various data from complex systems, thus, creating ample opportunity to integrate knowledge in many decision making applications. This dissertation introduces holistic learning as the integration of a comprehensive set of relationships that are used towards the learning objective. The holistic view of the problem allows for richer learning from data and, thereby, improves decision making.

The first topic of this dissertation is the prediction of several target attributes using a common set of predictor attributes. In a holistic learning approach, the relationships between target attributes are embedded into the learning algorithm created in this dissertation. Specifically, a novel tree based ensemble that leverages the relationships between target attributes towards constructing a diverse, yet strong, model is proposed. The method is justified through its connection to existing methods and experimental evaluations on synthetic and real data.

The second topic pertains to monitoring complex systems that are modeled as networks. Such systems present a rich set of attributes and relationships for which holistic learning is important. In social networks, for example, in addition to friendship ties, various attributes concerning the users' gender, age, topic of messages, time of messages, etc. are collected. A restricted form of monitoring fails to take the relationships of multiple attributes into account, whereas the holistic view embeds such relationships in the monitoring methods. The focus is on the difficult task to detect a change that might only impact a small subset of the network and only occur in a sub-region of the high-dimensional space of the network attributes. One contribution is a monitoring algorithm based on a network statistical model. Another contribution is a transactional model that transforms the task into an expedient structure for machine learning, along with a generalizable algorithm to monitor the attributed network. A learning step in this algorithm adapts to changes that may only be local to sub-regions (with a broader potential for other learning tasks). Diagnostic tools to interpret the change are provided. This robust, generalizable, holistic monitoring method is elaborated on synthetic and real networks.

Undeclared undergraduates participated in an experimental study designed to explore the impact of an Internet-delivered "growth mindset" training on indicators of women's engagement in science, engineering, technology, and mathematics ("STEM") disciplines. This intervention was hypothesized to increase STEM self-efficacy and intentions to pursue STEM by strengthening beliefs in intelligence as malleable ("IQ attitude") and discrediting gender-math stereotypes (strengthening "stereotype disbelief"). Hypothesized relationships between these outcome variables were specified in a path model. The intervention was also hypothesized to bolster academic achievement. Participants consisted of 298 women and 191 men, the majority of whom were self-identified as White (62%) and 18 years old (85%) at the time of the study. Comparison group participants received training on persuasive writing styles and control group participants received no training. Participants were randomly assigned to treatment, comparison, or control groups. At posttest, treatment group scores on measures of IQ attitude, stereotype disbelief, and academic achievement were highest; the effects of group condition on these three outcomes were statistically significant as assessed by analysis of variance. Results of pairwise comparisons indicated that treatment group IQ attitude scores were significantly higher than the average IQ attitude scores of both comparison and control groups. Treatment group scores on stereotype disbelief were significantly higher than those of the comparison group but not those of the control group. GPAs of treatment group participants were significantly higher than those of control group participants but not those of comparison group participants. The effects of group condition on STEM self-efficacy or intentions to pursue STEM were not significant. Results of path analysis indicated that the hypothesized model of the relationships between variables fit to an acceptable degree. However, a model with gender-specific paths from IQ attitude and stereotype disbelief to STEM self-efficacy was found to be superior to the hypothesized model. IQ attitude and stereotype disbelief were positively related; IQ attitude was positively related to men's STEM self-efficacy; stereotype disbelief was positively related to women's STEM self-efficacy, and STEM self-efficacy was positively related to intentions to pursue STEM. Implications and study limitations are discussed, and directions for future research are proposed.