Most research on Cognitive Load Theory (Sweller, 1988) has uncovered many instructional design considerations for learning complex tasks. Additionally, the Community of Inquiry (Garrison, Anderson, & Archer, 2000) framework describes many of the learning experiences in online education. A gap existed in the literature for investigating cognitive load over the duration of a college algebra course and for investigating the relationship between cognitive load and cognitive presence. This research study has addressed this gap by investigating cognitive load and cognitive presence in an online and face-to-face college algebra course. The results of this study revealed that face-to-face students earned statistically significant higher final course grades and homework grades than the online students. The face-to-face math course was slightly more efficient because it produced learners who exerted similar cognitive load as learners in the online course but the learners in the face-to-face earned higher performance score. Online discussion prompts that ask student to apply their solution or defend their solution engaged students in cognitive presence differently. When students were prompted to apply their solution to a real world scenario, most students reached resolution in their initial posts, but they were often not cognitively present in their follow-up posts. When students were prompted to provide a defense of their solution, most of the posts demonstrated cognitive presence, but not as many individual students reached resolution. Additionally, students progressed through the stages of cognitive presence when an instructor asked them a specific question about their math problem or real life scenario in a timely manner. When instructors post questions to their students that directly ask for an application of their hypothesis or an explanation how they arrived at their hypothesis, students can reach the highest stage of cognitive presence. When instructors post messages that reach the highest stage of cognitive presence, students do not post messages that reach the highest stage of cognitive presence. Lastly, this study did not find a strong linear relationship between cognitive presence and cognitive load.

The current study explores the interactions of cognitive load and stereotypes on emotions felt toward stereotyped groups and decisions of punitiveness for a crime. Dual processing models suggest that cognitive load can decrease deliberation and increase intuitive and emotional judgments. The Stereotype Content Model suggests that different stereotyped groups evoke different emotions. The current study tested the hypothesis that individuals under high cognitive load will be more likely to rely on stereotypical information and associated emotions when making decisions on punishment for a crime. Study 1 had 205 participants from Amazon’s Mechanical Turk website complete an online survey in which they read a vignette about an elderly man, a man who receives welfare checks, or a neutrally described man, who commits a “hit and run” crime. Half of the participants were then put under cognitive load, and all participants completed questions on punitiveness for the character’s crime, emotions felt towards the character, and perceptions of warmth and competence in the character. Study 2 repeated the manipulations and measures of study 1 with a few changes and in a college lab setting. Results were inconclusive in both studies and the null hypothesis was retained. Methodological and theoretical reasons for these results are discussed.

Research on the neural bases of cognitive deficits in autism spectrum disorder (ASD) has shown that working memory (WM) difficulties are associated with abnormalities in the prefrontal cortex. However, few studies have examined the impact of cognitive load on WM and its neural underpinnings in children and adolescents. We used fMRI and an n-back task with four levels of difficulty to compare the cortical activation patterns associated with WM in children with and without ASD across cognitive load. Findings revealed impaired modulated activity as a function of cognitive load in prefrontal and parietal cortices in children with ASD relative to typical controls. Results suggest that children with ASD rely mainly on posterior brain regions associated with lower-level visual processing, whereas controls showed activity in frontal lobes related to the classic WM network. Findings will help guide future longitudinal work by localizing areas of vulnerability to developmental disturbances.

Research on the neural bases of cognitive deficits in autism spectrum disorder (ASD) has shown that working memory (WM) difficulties are associated with abnormalities in the prefrontal cortex. However, few studies have examined the impact of cognitive load on WM and its neural underpinnings in children and adolescents. We used fMRI and an n-back task with four levels of difficulty to compare the cortical activation patterns associated with WM in children with and without ASD across cognitive load. Findings revealed impaired modulated activity as a function of cognitive load in prefrontal and parietal cortices in children with ASD relative to typical controls. Results suggest that children with ASD rely mainly on posterior brain regions associated with lower-level visual processing, whereas controls showed activity in frontal lobes related to the classic WM network. Findings will help guide future longitudinal work by localizing areas of vulnerability to developmental disturbances.

The purpose of the study was to investigate the application of cognitive load theory to the design of online instruction. Students in three different courses (N = 146) were measured on both learning performance and perceptions of mental effort to see if there were any statistically significant differences. The study utilized a quasi-experimental posttest-only control group design contrasting modified and unmodified instructional lessons. Both groups were given a posttest to measure knowledge gained from the lesson (cognitive domain of learning) and perceptions of mental effort involved. Independent samples t-tests were used to compare the mean performance scores of the treatment groups (i.e. the sections using redesigned materials) versus the control groups for all three courses. Cohen's d was also computed to determine effect size. Mental effort scores were similarly compared for each group on the overall cognitive load score, for a total of six data points in the study. Of the four hypotheses examined, three (H1, H2, H4) found no statistically significant difference between the experimental and control groups. Negative significance was found between the experimental and control group on the effect of modality (H3). On measures of cognitive load, no statistically significant differences were found.

This is a study of the influence of the familiarity of students with the narrator of video tutorials, in a blended learning situation, on both the perceived and actual effectiveness of the learning materials, in terms of students’ learning efficiency – where a course is traditional in format and online learning is carried out with the help of Narrated Video Screen Captures (NVSCs). The study also focused on the interaction of student-narrator gender similarity and students’ individual differences (conscientiousness and test-anxiety) with voice familiarity. Thus, the study sought to fill a gap in knowledge regarding the influence of familiarity with the narrator in multimedia learning material on the efficiency of learning within a blended learning context. The research paradigm was deductive, employing a mixed methods and a case study research and using quasi-experiments. In order to compare the relational efficiency of the different instructional conditions, a calculative approach was used that combined measurement of mental effort with task performance. In addition to the mental effort questionnaires and task performance, students completed an assessment questionnaire for the NVSCs. In addition, semi-structured interviews and a follow-up questionnaire were used for collection of corroborative data, in order to shed more light on this matter. Findings showed significant influence of voice familiarity on most of the learning efficiency indices and on perceived effectiveness of NVSCs. Gender similarity was significant only with unfamiliar voice and there was no significant interaction between conscientiousness and test anxiety and voice familiarity. Thus, it was concluded that when students have a personal relationship with the class teacher, exposure to multimedia learning materials with an unfamiliar narrator has an adverse influence on their learning efficiency. These findings add to the established voice related principles of Cognitive Theory of Multimedia Learning and Social Agency Theory. Contribution to knowledge was made by filling the gap in knowledge in the area of multimedia instructional design.

Recent technological advances have witnessed the rapid encroachment of computing systems into our social spaces. Their acceptance in these social spaces by other occupants, however, might be mostly contingent on their social appropriateness. Notions of social appropriateness might seem vague but even people who don’t act on this commonsense knowledge, and accord to social norms, can sometimes find themselves ostracized from society. It is reflected in behavior that supports a sense of successful engagement and connection. Such behavior communicates a desire to be accepted and a willingness to engage, as opposed to inappropriateness that conveys indifference, rejection or even danger. As social actors, how can systems improve their interactions with us in order to better succeed at their tasks? Perhaps, more interestingly, how might they even improve our communications with each other? In this thesis we describe a framework to identify opportunities to design systems that can begin to act appropriately in social settings, which we call Considerate Systems. It includes a design process and guidelines, which allows an interaction to be viewed from the perspectives of the user, system and task. It also includes an architecture that guides the addition of productive social responses to interactive systems. We demonstrate the utility of this framework by exploring two types of scenarios that impact social interactions in contrasting ways. Remote interactions (such as on a conference call) suffer from an impinging of social cues that people rely on while communicating. On the other hand, situated multitasking interactions (such as texting while driving) can easily overwhelm users and detract from their performance. The framework is applied towards the design of autonomous agents tackling problems endemic to such scenarios. We evaluate their success with respect to specific scenario goals. We conclude by noting that while the challenges of instilling computing systems with a sense of appropriateness seem daunting, our productive use of systems can be enhanced with them.

The protection of proprietary information that users print from their information systems is a significant and relevant concern in the field of information security to both researchers and practitioners. Information security researchers have repeatedly indicated that human behaviors and perception are important factors influencing the information security of organizations and have called for more research. The aerospace and defense industry commonly deals with its own proprietary information as well its customers. Further, e-training is a growing practice in this industry, it frequently deals with proprietary information, and has unique information security challenge, thus, serves as additional context for this study. This study focused on the investigation of two constructs, user reading preference and user perceived risk of compromising printed proprietary information, as well as seven user demographics. These constructs reflect human behavior and risk perceptions associated with compromising printed proprietary information and, thus, provide valuable insights applicable into information security. This study developed a Reading Preference and Risk (RPR) Taxonomy, which allows users to be classified according to the aforementioned two constructs under investigation and provides insightful characterizations of information security risks. A survey based on existing literature, the primary constructs, and several demographics was implemented to assess two research questions and seven associated hypotheses. The survey was sent to 1,728 employees of an aerospace and defense organization. The response rate was 18% with 311 usable records. The results of the study showed that employees were dispersed across the RPR Taxonomy with 15.1% identified as potentially problematic to the protection of printed proprietary information. The overall results showed that the population had a reading preference for print materials and a high perceived risk for compromising printed proprietary information, as well as significantly higher print preference for e-training materials when it was necessary to retain the content in memory. Significant differences in the two constructs were also found across several demographics including age, gender, frequency of user exposure to proprietary information, the confidentiality level of the proprietary information a user is regularly exposed to, and previous user experience with the compromise of proprietary information. Recommendations for practice and research are provided. Moreover, several areas for future research are also presented.

As the amount of information captured about users increased over the last decade, interest in personalized user interfaces has surged in the HCI and IS communities. Personalization is an effective means for accommodating for differences between individuals. The fundamental idea behind personalization rests on the notion that if a system can gather useful information about the user, generate a relevant user model and apply it appropriately, it would be possible to adapt the behavior of a system and its interface to the user at the individual level. Personal-ization of a user interface features can enhance usability. With recent technological advances, personalization can be achieved automatically and unobtrusively. A user interface can deploy a NeuroIS technology such as eye-tracking that learns from the user's visual behavior to provide users an experience most unique to them. The advantage of eye-tracking technology is that subjects cannot consciously manipulate their responses since they are not readily subject to manipulation. The objective of this dissertation is to develop a theoretical framework for user personalization during reading comprehension tasks based on two machine learning (ML) models. The proposed ML-based profiling process consists of user's age characterization and user's cognitive load detection, while the user reads text. To this end, detection of cognitive load through eye-movement features was investigated during different cognitive tasks (see Chapters 3, 4 and 6) with different task conditions. Furthermore, in separate studies (see Chapters 5 and 6) the relationship between user's eye-movements and their age population (e.g., younger and older generations) were carried out during a reading comprehension task. A Tobii X300 eye tracking device was used to record the eye movement data for all studies. Eye-movement data was acquired via Tobii eye tracking software, and then preprocessed and analyzed in R for the aforementioned studies. Machine learning techniques were used to build predictive models. The aggregated results of the studies indicate that machine learning accompanied with a NeuroIS tool like eye-tracking, can be used to model user characteristics like age and user mental states like cognitive load, automatically and implicitly with accuracy above chance (range of 70-92%). The results of this dissertation can be used in a more general framework to adaptively modify content to better serve the users mental and age needs. Text simplification and modification techniques might be developed to be used in various scenarios.

Jag har i denna studie haft som syfte att undersöka hur förmågan att skriva för hand ser ut för elever i mellanstadieålder i en svensk grundskola. Mitt syfte har också varit att undersöka om det finns ett samband mellan förmågan att skriva för hand och förmågan att skriva med textkvalitet. För att nå svar på mina frågeställningar genomförde jag en undersökning där 25 elever deltog. Undersökningen innehöll fyra testdelar som vardera var designade för att mäta olika delar i förmågan att skriva för hand och även ämnade att synliggöra förmågan att skriva med textkvalitet. Den forskning som ligger till grund för den här studien visar att det finns ett samband mellan en automatiserad förmåga att skriva för hand, förmåga att skriva med textkvalitet och skolframgång. Orsaken till detta samband förklaras av forskningen i hur olika minnesstrukturer kan användas och avlastas vid automatiserade förmågor jämfört med icke automatiserade förmågor. Resultatet av studien visar att det finns en stor variation i den undersökta elevgruppens förmåga att skriva för hand. Tydliga tendenser pekar även på att det finns ett samband mellan en automatiserad förmåga att skriva för hand och en förmåga att skriva med textkvalitet.