Search

Eye movements provide a window into cognitive processes, but much of the research harnessing this data has been confined to the laboratory. We address whether eye gaze can be passively, reliably, and privately recorded in real-world environments across extended timeframes using commercial-off-the-shelf (COTS) sensors. We recorded eye gaze data from a COTS tracker embedded in participants (N=20) work environments at pseudorandom intervals across a two-week period. We found that valid samples were recorded approximately 30% of the time despite calibrating the eye tracker only once and without placing any other restrictions on participants. The number of valid samples decreased over days with the degree of decrease dependent on contextual variables (i.e., frequency of video conferencing) and individual difference attributes (e.g., sleep quality and multitasking ability). Participants reported that sensors did not change or impact their work. Our findings suggest the potential for the collection of eye-gaze in authentic environments.

Psychological science can benefit from and contribute to emerging approaches from the computing and information sciences driven by the availability of real-world data and advances in sensing and computing. We focus on one such approach, machine-learned computational models (MLCMs)—computer programs learned from data, typically with human supervision. We introduce MLCMs and discuss how they contrast with traditional computational models and assessment in the psychological sciences. Examples of MLCMs from cognitive and affective science, neuroscience, education, organizational psychology, and personality and social psychology are provided. We consider the accuracy and generalizability of MLCM-based measures, cautioning researchers to consider the underlying context and intended use when interpreting their performance. We conclude that in addition to known data privacy and security concerns, the use of MLCMs entails a reconceptualization of fairness, bias, interpretability, and responsible use.

The ability to identify whether a user is “zoning out” (mind wandering) from video has many HCI (e.g., distance learning, high-stakes vigilance tasks). However, it remains unknown how well humans can perform this task, how they compare to automatic computerized approaches, and how a fusion of the two might improve accuracy. We analyzed videos of users’ faces and upper bodies recorded 10s prior to self-reported mind wandering (i.e., ground truth) while they engaged in a computerized reading task. We found that a state-of-the-art machine learning model had comparable accuracy to aggregated judgments of nine untrained human observers (area under receiver operating characteristic curve [AUC] = .598 versus .589). A fusion of the two (AUC = .644) outperformed each, presumably because each focused on complementary cues. Furthermore, adding more humans beyond 3–4 observers yielded diminishing returns. We discuss implications of human–computer fusion as a means to improve accuracy in complex tasks.

We provide a psychometric-grounded exposition of bias and fairness as applied to a typical machine learning pipeline for affective computing. We expand on an interpersonal communication framework to elucidate how to identify sources of bias that may arise in the process of inferring human emotions and other psychological constructs from observed behavior. Various methods and metrics for measuring fairness and bias are discussed along with pertinent implications within the United States legal context. We illustrate how to measure some types of bias and fairness in a case study involving automatic personality and hireability inference from multimodal data collected in video interviews for mock job applications. We encourage affective computing researchers and practitioners to encapsulate bias and fairness in their research processes and products and to consider their role, agency, and responsibility in promoting equitable and just systems., 21 pages, 4 figures

We report two studies that used facial features to automatically detect mind wandering, a ubiquitous phenomenon whereby attention drifts from the current task to unrelated thoughts. In a laboratory study, university students $(N = 152)$ read a scientific text, whereas in a classroom study high school students $(N = 135)$ learned biology from an intelligent tutoring system. Mind wandering was measured using validated self-report methods. In the lab, we recorded face videos and analyzed these at six levels of granularity: (1) upper-body movement; (2) head pose; (3) facial textures; (4) facial action units (AUs); (5) co-occurring AUs; and (6) temporal dynamics of AUs. Due to privacy constraints, videos were not recorded in the classroom. Instead, we extracted head pose, AUs, and AU co-occurrences in real-time. Machine learning models, consisting of support vector machines (SVM) and deep neural networks, achieved $F_{1}$ scores of .478 and .414 (25.4 and 20.9 percent above-chance improvements, both with SVMs) for detecting mind wandering in the lab and classroom, respectively. The lab-based detectors achieved 8.4 percent improvement over the previous state-of-the-art; no comparison is available for classroom detectors. We discuss how the detectors can integrate into intelligent interfaces to increase engagement and learning by responding to wandering minds.

Collaborative problem-solving (CPS) is ubiquitous in everyday life, including work, family, leisure activities, etc. With collaborations increasingly occurring remotely, next-generation collaborative interfaces could enhance CPS processes and outcomes with dynamic interventions or by generating feedback for after-action reviews. Automatic modeling of CPS processes (called facets here) is a precursor to this goal. Accordingly, we build automated detectors of three critical CPS facets—construction of shared knowledge, negotiation and coordination, and maintaining team function—derived from a validated CPS framework. We used data of 32 triads who collaborated via a commercial videoconferencing software, to solve challenging problems in a visual programming task. We generated transcripts of 11,163 utterances using automatic speech recognition, which were then coded by trained humans for evidence of the three CPS facets. We used both standard and deep sequential learning classifiers to model the human-coded facets from linguistic, task context, facial expressions, and acoustic–prosodic features in a team-independent fashion. We found that models relying on nonverbal signals yielded above-chance accuracies (area under the receiver operating characteristic curve, AUROC) ranging from .53 to .83, with increases in model accuracy when language information was included (AUROCS from .72 to .86). There were no advantages of deep sequential learning methods over standard classifiers. Overall, Random Forest classifiers using language and task context features performed best, achieving AUROC scores of .86, .78, and .79 for construction of shared knowledge, negotiation/coordination, and maintaining team function, respectively. We discuss application of our work to real-time systems that assess CPS and intervene to improve CPS outcomes.

Whereas social visual attention has been examined in computer-mediated (e.g., shared screen) or video-mediated (e.g., FaceTime) interaction, it has yet to be studied in mixed-media interfaces that combine video of the conversant along with other UI elements. We analyzed eye gaze of 37 dyads (74 participants) who were tasked with negotiating the price of a new car (as a buyer and seller) using mixed-media video conferencing under competitive or cooperative negotiation instructions (experimental manipulation). We used multidimensional recurrence quantification analysis to extract spatio-temporal patterns corresponding to mutual gaze (individuals look at each other), joint attention (individuals focus on the same elements of the interface), and gaze aversion (an individual looks at their partner, who is looking elsewhere). Our results indicated that joint attention predicted the sum of points attained by the buyer and seller (i.e., the joint score). In contrast, gaze aversion was associated with faster time to complete the negotiation, but with a lower joint score. Unexpectedly, mutual gaze was highly infrequent and unrelated to the negotiation outcomes and none of the gaze patterns predicted subjective perceptions of the negotiation. There were also no effects of gender composition or negotiation condition on the gaze patterns or negotiation outcomes. Our results suggest that social visual attention may operate differently in mixed-media collaborative interfaces than in face-to-face interaction. As mixed-media collaborative interfaces gain prominence, our work can be leveraged to inform the design of gaze-sensitive user interfaces that support remote negotiations among other tasks.

During mind wandering, visual processing of external information is attenuated. Accordingly, mind wandering is associated with changes in gaze behaviors, albeit findings are inconsistent in the literature. This heterogeneity obfuscates a complete view of the moment-to-moment processing priorities of the visual system during mind wandering. We hypothesize that this observed heterogeneity is an effect of idiosyncrasy across tasks with varying spatial allocation demands, visual processing demands, and discourse processing demands and reflects a strategic, compensatory shift in how the visual system operates during mind wandering. We recorded eye movements and mind wandering (via thought-probes) as 132 college-aged adults completed a battery of 7 short (6 min) tasks with different visual demands. We found that for tasks requiring extensive sampling of the visual field, there were fewer fixations, and, depending on the specific task, fixations were longer and/or more dispersed. This suggests that visual sampling is sparser and potentially slower and more dispersed to compensate for the decreased sampling rate during mind wandering. For tasks that demand centrally focused gaze, mind wandering was accompanied by more exploratory eye movements, such as shorter and more dispersed fixations as well as larger saccades. Gaze behaviors were not reliably associated with mind wandering during a film comprehension task. These findings provide insight into how the visual system prioritizes external information when attention is focused inward and indicates the importance of task demands when assessing the relationship between eye movements, visual processing, and mind wandering. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

The prevalence of the acronym tl;dr (“too long; didn’t read”) suggests that people intentionally disengage their attention from long sections of text. We studied this real-world phenomenon in an ed...

We propose that machine-learned computational models (MLCMs), in which the model parameters and perhaps even structure are learned from data, can complement extant approaches to the study of text a...

Affect detection in the "real" wild - where people go about their daily routines in their homes and workplaces - is arguably a different problem than affect detection in the lab or in the "quasi" wild (e.g., YouTube videos). How will our affect detection systems hold up when put to the test in the real wild? Some in the Affective Computing community had an opportunity to address this question as part of the MOSAIC (Multimodal Objective Sensing to Assess Individuals with Context [1]) program which ran from 2017 to 2020. Results were sobering, but informative. I'll discuss those efforts with an emphasis on performance achieved, insights gleaned, challenges faced, and lessons learned.

We introduce the psychometric concepts of bias and fairness in a multimodal machine learning context assessing individuals’ hireability from prerecorded video interviews. We collected interviews from 733 participants and hireability ratings from a panel of trained annotators in a simulated hiring study, and then trained interpretable machine learning models on verbal, paraverbal, and visual features extracted from the videos to investigate unimodal versus multimodal bias and fairness. Our results demonstrate that, in the absence of any bias mitigation strategy, combining multiple modalities only marginally improves prediction accuracy at the cost of increasing bias and reducing fairness compared to the least biased and most fair unimodal predictor set (verbal). We further show that gender-norming predictors only reduces gender predictability for paraverbal and visual modalities, while removing gender-biased features can achieve gender blindness, minimal bias, and fairness (for all modalities except for visual) at the cost of some prediction accuracy. Overall, the reduced-feature approach using predictors from all modalities achieved the best balance between accuracy, bias, and fairness, with the verbal modality alone performing almost as well. Our analysis highlights how optimizing model prediction accuracy in isolation and in a multimodal context may cause bias, disparate impact, and potential social harm, while a more holistic optimization approach based on accuracy, bias, and fairness can avoid these pitfalls.

This study answered novel questions about the connection between high school extracurricular dosage (number of activities and participation duration) and the attainment of a bachelor's degree. Using data from the Common Application and the National Student Clearinghouse (N = 311,308), we found that greater extracurricular participation positively predicted bachelor's degree attainment. However, among students who ultimately earned a bachelor's degree, participating in more than a moderate number of high school activities (3 or 4) predicted decreasing odds of earning a bachelor's degree on time (within 4 years). This effect intensified as participation duration increased, such that students who participated in the greatest number of high school activities for the most years were the most likely to delay college graduation.

We zone out roughly 20-40% of the time during reading – a rate that is concerning given the negative relationship between mind-wandering and comprehension. We tested if Eye-Mind Reader – an intelli...

Several psychologists posit that performance is not only a function of personality but also of situational contexts, such as day-level activities. Yet in practice, since only personality assessments are used to infer job performance, they provide a limited perspective by ignoring activity. However, multi-modal sensing has the potential to characterize these daily activities. This paper illustrates how empirically measured activity data complements traditional effects of personality to explain a worker's performance. We leverage sensors in commodity devices to quantify the activity context of 603 information workers. By applying classical clustering methods on this multisensor data, we take a person-centered approach to describe workers in terms of both personality and activity. We encapsulate both these facets into an analytical framework that we call organizational personas. On interpreting these organizational personas we find empirical evidence to support that, independent of a worker's personality, their activity is associated with job performance. While the effects of personality are consistent with the literature, we find that the activity is equally effective in explaining organizational citizenship behavior and is less but significantly effective for task proficiency and deviant behaviors. Specifically, personas that exhibit a daily-activity pattern with fewer location visits, batched phone-use, shorter desk-sessions and longer sleep duration, tend to perform better on all three performance metrics. Organizational personas are a descriptive framework to identify the testable hypotheses that can disentangle the role of malleable aspects like activity in determining the performance of a worker population.

Collaborative problem solving (CPS) is a crucial 21st century skill; however, current technologies fall short of effectively supporting CPS processes, especially for remote, computer-enabled interactions. In order to develop next-generation computer-supported collaborative systems that enhance CPS processes and outcomes by monitoring and responding to the unfolding collaboration, we investigate automated detection of three critical CPS process ? construction of shared knowledge, negotiation/coordination, and maintaining team function ? derived from a validated CPS framework. Our data consists of 32 triads who were tasked with collaboratively solving a challenging visual computer programming task for 20 minutes using commercial videoconferencing software. We used automatic speech recognition to generate transcripts of 11,163 utterances, which trained humans coded for evidence of the above three CPS processes using a set of behavioral indicators. We aimed to automate the trained human-raters' codes in a team-independent fashion (current study) in order to provide automatic real-time or offline feedback (future work). We used Random Forest classifiers trained on the words themselves (bag of n-grams) or with word categories (e.g., emotions, thinking styles, social constructs) from the Linguistic Inquiry Word Count (LIWC) tool. Despite imperfect automatic speech recognition, the n-gram models achieved AUROC (area under the receiver operating characteristic curve) scores of .85, .77, and .77 for construction of shared knowledge, negotiation/coordination, and maintaining team function, respectively; these reflect 70%, 54%, and 54% improvements over chance. The LIWC-category models achieved similar scores of .82, .74, and .73 (64%, 48%, and 46% improvement over chance). Further, the LIWC model-derived scores predicted CPS outcomes more similar to human codes, demonstrating predictive validity. We discuss embedding our models in collaborative interfaces for assessment and dynamic intervention aimed at improving CPS outcomes.

We conducted an exploratory study on affect regulation during game-based learning where 110 college-aged participants (Mage = 22.14, SDage = 1.24; 50.0% female; 70.0% White) played an easy, medium, and difficult level of an educational game (Physics Playground) while self-reporting their strongest affective state and regulation strategies associated with each level. Participants also self-reported their effort and completed a physics posttest after gameplay. We found that frustration, confusion, determination, and curiosity were the dominant affective states (81.4% of total reports) while cognitive reappraisal and acceptance were the major affective regulation strategies (others individually occurred less than 10.1% of the time). Engaging in cognitive reappraisal – an affective regulation strategy that involves changing the way one thinks about a situation – was beneficial for successfully solving a level when participants were frustrated or confused, but had no effect when participants were determined or curious. Engaging in cognitive reappraisal when experiencing high frustration/confusion positively predicted posttest scores, but only for those who put a high amount of effort into the game. For students who were low in effort or low in frustration/confusion, simply accepting one's emotions when experiencing high frustration/confusion was beneficial. We discuss theoretical implications and applications towards game-based learning supports to promote persistence and learning outcomes.

Virtual learning environments (VLEs) are increasingly used at-scale in educational contexts to facilitate teaching and promote learning, and the data they produce can be used for educationa...

Mental health issues, which can be difficult to diagnose, are a growing concern worldwide. For effective care and support, early detection of mood-related health concerns is of paramount importance. Typically, survey based instruments including Ecologically Momentary Assessments (EMA) and Day Reconstruction Method (DRM) are the method of choice for assessing mood related health. While effective, these methods require some effort and thus both compliance rates as well as quality of responses can be limited. As an alternative, We present a study that used passively sensed data from smartphones and wearables and machine learning techniques to predict mood instabilities, an important aspect of mental health. We explored the effectiveness of the proposed method on two large-scale datasets, finding that as little as three weeks of continuous, passive recordings were sufficient to reliably predict mood instabilities.

Achieving important goals is widely assumed to require confronting obstacles, failing repeatedly, and persisting in the face of frustration. Yet empirical evidence linking achievement and frustration tolerance is lacking. To facilitate work on this important topic, we developed and validated a novel behavioral measure of frustration tolerance: the Mirror Tracing Frustration Task (MTFT). In this 5-min task, participants allocate time between a difficult tracing task and entertaining games and videos. In two studies of young adults (Study 1: N = 148, Study 2: N = 283), we demonstrated that the MTFT increased frustration more than 18 other emotions, and that MTFT scores were related to self-reported frustration tolerance. Next, we assessed whether frustration tolerance correlated with similar constructs, including self-control and grit, as well as objective measures of real-world achievement. In a prospective longitudinal study of high-school seniors (N = 391), MTFT scores predicted grade-point average and standardized achievement test scores, and-more than 2 years after completing the MTFT-progress toward a college degree. Though small in size (i.e., rs ranging from .10 to .24), frustration tolerance predicted outcomes over and above a rich set of covariates, including IQ, sociodemographics, self-control, and grit. These findings demonstrate the validity of the MTFT and highlight the importance of frustration tolerance for achieving valued goals. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Assessing performance in the workplace typically relies on subjective evaluations, such as, peer ratings, supervisor ratings and self assessments, which are manual, burdensome and potentially biased. We use objective mobile sensing data from phones, wearables and beacons to study workplace performance and offer new insights into behavioral patterns that distinguish higher and lower performers when considering roles in companies (i.e., supervisors and non-supervisors) and different types of companies (i.e., high tech and consultancy). We present initial results from an ongoing year-long study of N=554 information workers collected over a period ranging from 2-8.5 months. We train a gradient boosting classifier that can classify workers as higher or lower performers with AUROC of 0.83. Our work opens the way to new forms of passive objective assessment and feedback to workers to potentially provide week by week or quarter by quarter guidance in the workplace.

We investigate the use of commercial off-the-shelf (COTS) eye-trackers to automatically detect mind wandering—a phenomenon involving a shift in attention from task-related to task-unrelated thoughts—during computerized learning. Study 1 (N = 135 high-school students) tested the feasibility of COTS eye tracking while students learn biology with an intelligent tutoring system called GuruTutor in their classroom. We could successfully track eye gaze in 75% (both eyes tracked) and 95% (one eye tracked) of the cases for 85% of the sessions where gaze was successfully recorded. In Study 2, we used this data to build automated student-independent detectors of mind wandering, obtaining accuracies (mind wandering F1 = 0.59) substantially better than chance (F1 = 0.24). Study 3 investigated context-generalizability of mind wandering detectors, finding that models trained on data collected in a controlled laboratory more successfully generalized to the classroom than the reverse. Study 4 investigated gaze- and video- based mind wandering detection, finding that gaze-based detection was superior and multimodal detection yielded an improvement in limited circumstances. We tested live mind wandering detection on a new sample of 39 students in Study 5 and found that detection accuracy (mind wandering F1 = 0.40) was considerably above chance (F1 = 0.24), albeit lower than offline detection accuracy from Study 1 (F1 = 0.59), a finding attributable to handling of missing data. We discuss our next steps towards developing gaze-based attention-aware learning technologies to increase engagement and learning by combating mind wandering in classroom contexts.

Compared with admissions test scores, why are high school grades better at predicting college graduation? We argue that success in college requires not only cognitive ability but also self-regulatory competencies that are better indexed by high school grades. In a national sample of 47,303 students who applied to college for the 2009/2010 academic year, Study 1 affirmed that high school grades out-predicted test scores for 4-year college graduation. In a convenience sample of 1,622 high school seniors in the Class of 2013, Study 2 revealed that the incremental predictive validity of high school grades for college graduation was explained by composite measures of self-regulation, whereas the incremental predictive validity of test scores was explained by composite measures of cognitive ability.

We designed and tested an attention-aware learning technology (AALT) that detects and responds to mind wandering (MW), a shift in attention from task-related to task-unrelated thoughts, that is negatively associated with learning. We leveraged an existing gaze-based mind wandering detector that uses commercial off the shelf eye tracking to inform real-time interventions during learning with an Intelligent Tutoring System in real-world classrooms. The intervention strategies, co-designed with students and teachers, consisted of using student names, reiterating content, and asking questions, with the aim to reengage wandering minds and improve learning. After several rounds of iterative refinement, we tested our AALT in two classroom studies with 287 high-school students. We found that interventions successfully reoriented attention, and compared to two control conditions, reduced mind wandering, and improved retention (measured via a delayed assessment) for students with low prior-knowledge who occasionally (but not excessively) mind wandered. We discuss implications for developing gaze-based AALTs for real-world contexts.

Students using online learning environments need to effectively self-regulate their learning. However, with an absence of teacher-provided structure, students often resort to less effective, passive learning strategies versus constructive ones. We consider the potential benefits of interventions that promote retrieval practice – retrieving learned content from memory – which is an effective strategy for learning and retention. The goal is to nudge students towards completing short, formative quizzes when they are likely to succeed on those assessments. Towards this goal, we developed a machine-learning model using data from 32,685 students who used an online mathematics platform over an entire school year to prospectively predict scores on three-item assessments (N = 210,020) from interaction patterns up to 9 minutes before the assessment as well as Item Response Theory (IRT) estimates of student ability and quiz difficulty. These models achieved a student-independent correlation of 0.55 between predicted and actual scores on the assessments and outperformed IRT-only predictions (r = 0.34). Model performance was largely independent of the length of the analyzed window preceding a quiz. We discuss potential for future applications of the models to trigger dynamic interventions that aim to encourage students to engage with formative assessments rather than more passive learning strategies.

Teachers, like everyone else, need objective reliable feedback in order to improve their effectiveness. However, developing a system for automated teacher feedback entails many decisions regarding data collection procedures, automated analysis, and presentation of feedback for reflection. We address the latter two questions by comparing two different machine learning approaches to automatically model seven features of teacher discourse (e.g., use of questions, elaborated evaluations). We compared a traditional open-vocabulary approach using n-grams and Random Forest classifiers with a state-of-the-art deep transfer learning approach for natural language processing (BERT). We found a tradeoff between data quantity and accuracy, where deep models had an advantage on larger datasets, but not for smaller datasets, particularly for variables with low incidence rates. We also compared the models based on the level of feedback granularity: utterance-level (e.g., whether an utterance is a question or a statement), class session-level proportions by averaging across utterances (e.g., question incidence score of 48%), and session-level ordinal feedback based on pre-determined thresholds (e.g., question asking score is medium [vs. low or high]) and found that BERT generally provided more accurate feedback at all levels of granularity. Thus, BERT appears to be the most viable approach to providing automatic feedback on teacher discourse provided there is sufficient data to fine tune the model.

Emotional regularity is the degree to which a person maintains and returns to a set of emotional states over time. The present investigation examined associations between emotional regularity and extant emotion measures as well as psychologically relevant dimensions of personality, health, and real-world occupational outcomes. Participants included 598 U.S. adults who provided daily experience sampling reports on their emotional states for approximately two months. Results suggest that emotional regularity was related to, but distinct from, well-established measures of emotion including emotional intensity, variability, covariation, inertia, granularity, and emodiversity. Furthermore, emotional regularity significantly predicted measures of personality, psychological health, and occupational outcomes even when accounting for extant emotion measures and sociodemographic covariates. Finally, it explained modest (7.5%) improvement (in terms of cross-validated RSq.) over baseline models containing emotional intensity, variability, and sociodemographic covariates. These findings suggest that emotional regularity may provide an important indicator of healthy emotional functioning and may be a promising area for further scientific discovery.

Digital learning technologies that aim to measure and sustain student engagement typically use supervised machine learning approaches for engagement detection, which requires reliable “ground-truth” engagement annotations. The present study examined associations between student demographics (age [grade], gender, and ethnicity) and the reliability of engagement annotations based on visual behaviors. We collected videos of diverse students (N = 60) from grades 1–12 who engaged in one-hour online learning sessions with grade-appropriate content. Each student’s data was annotated by three trained coders for behavioral and emotional engagement. We found that inter-rater reliability (IRR) for behavioral engagement was higher for older students whereas IRRs for emotional engagement was higher for younger students. We also found that both rotational head movements and facial expressivity decreased with age, and critically, rotational head movements mediated the effects of grade on behavioral IRR; there was no mediation for emotional IRR. There were no effects of gender or ethnicity on IRR. We discuss the implications of our findings for annotating engagement in supervised learning models for diverse students and across grades.

Human abnormal physical and psychological behaviors, such as high level of stress, may result in negative impacts on work and life, if not handled efficiently. However, the continuous collection of behavioral data from questionnaires is not feasible, as is often the case for the natural downside of survey data gathering. Thanks to the proliferation of mobile sensors, it brings compelling opportunities for us to more deeply analyze human behavior. In this work, we ask the question of detecting anomalies in human physical and psychological behaviors from multivariate temporal data from multi-modal sensors. In the past decades, many efforts have been made in developing anomaly detection methods, but there remain several challenges in this specific domain problem: 1) data contains missing values at random positions. 2) data from multiple sensors is of multi-resolution and multivariate. 3) human behaviors are correlated to each other, thus it poses a multi-label problem. 4) the available labeled instances are limited, which requires the semi-supervised learning setting. 5) the frequency of anomaly occurrence is much smaller than that of normal instances, leading to imbalance problems. We propose a novel framework MBead to resolve these concerns. MBead consists of three key components: reweighted autoencoder to capture the dependency across temporal domain and multiple modalities, relevance learning module to learn the pairwise relations among labeled instances, and temporal prediction module to detect the anomalies while trained in semi-supervised settings. Extensive experiments show our MBead outperforms seven state-of-art baselines on three tasks of behavior anomaly detection: stress, affect, and work performance.

Modeling team phenomena from multiparty interactions inherently requires combining signals from multiple teammates, often by weighting strategies. Here, we explored the hypothesis that strategic weighting signals from individual teammates would outperform an equal weighting baseline. Accordingly, we explored role-, trait-, and behavior-based weighting of behavioral signals across team members. We analyzed data from 101 triads engaged in computer-mediated collaborative problem solving (CPS) in an educational physics game. We investigated the accuracy of machine-learned models trained on facial expressions, acoustic-prosodics, eye gaze, and task context information, computed one-minute prior to the end of a game level, at predicting success at solving that level. AUROCs for unimodal models that equally weighted features from the three teammates ranged from .54 to .67, whereas a combination of gaze, face, and task context features, achieved an AUROC of .73. The various multiparty weighting strategies did not outperform an equal-weighting baseline. However, our best nonverbal model (AUROC = .73) outperformed a language-based model (AUROC = .67), and there were some advantages to combining the two (AUROC = .75). Finally, models aimed at prospectively predicting performance on a minute-by-minute basis from the start of the level achieved a lower, but still above-chance, AUROC of .60. We discuss implications for multiparty modeling of team performance and other team constructs.

Like anyone, teachers need feedback to improve. Due to the high cost of human classroom observation, teachers receive infrequent feedback which is often more focused on evaluating performance than on improving practice. To address this critical barrier to teacher learning, we aim to provide teachers with detailed and actionable automated feedback. Towards this end, we developed an approach that enables teachers to easily record high-quality audio from their classes. Using this approach, teachers recorded 142 classroom sessions, of which 127 (89%) were usable. Next, we used speech recognition and machine learning to develop teacher-generalizable computer-scored estimates of key dimensions of teacher discourse. We found that automated models were moderately accurate when compared to human coders and that speech recognition errors did not influence performance. We conclude that authentic teacher discourse can be recorded and analyzed for automatic feedback. Our next step is to incorporate the automatic models into an interactive visualization tool that will provide teachers with objective feedback on the quality of their discourse.

In an increasingly globalized and service-oriented economy, people need to engage in computer-mediated collaborative problem solving (CPS) with diverse teams. However, teams routinely fail to live up to expectations, showcasing the need for technologies that help develop effective collaboration skills. We take a step in this direction by investigating how different dimensions of team diversity (demographic, personality, attitudes towards teamwork, prior domain experience) predict objective (e.g. effective solutions) and subjective (e.g. positive perceptions) collaborative outcomes. We collected data from 96 triads who engaged in a 30-minute CPS task via videoconferencing. We found that demographic diversity and differing attitudes towards teamwork predicted impressions of positive engagement, while personality diversity predicted learning outcomes. Importantly, these relationships were maintained after accounting for team makeup. None of the diversity measures predicted task performance. We discuss how our findings can be incorporated into technologies that aim to help diverse teams develop CPS skills.

We conducted a meta-analysis of 33 independent samples (N = 2924) to address whether adding anthropomorphic faces to multimedia graphics and/or adding pleasant colors are effective emotional design approaches. We found significant positive meta-analytic effects for retention (k = 18, d+ = 0.387), comprehension (k = 14, d+ = 0.317), and transfer (k = 27, d+ = 0.327) under a random-effects model. Effects for affective-motivational variables were mixed, with a robust effect for intrinsic motivation (k = 23, d+ = 0.255), a weaker effect for liking/enjoyment (k = 20, d+ = 0.109), and a marginal effect for positive affect (k = 15, d+ = 0.113). The manipulations did not significantly (ps > .227) influence perceptions of learning (k = 11, d+ = 0.097) or effort (k = 20, d+ = 0.051), but reduced perceptions of difficulty (k = 14, d+ = −0.208). Four of the outcome variables (retention, transfer, intrinsic motivation, and perceived effort) were sufficiently heterogeneous. There was no major issue with publication bias, influential cases, or outliers. With one exception, there was no evidence of moderation by experimental contrast, dynamicity of materials, age, language/culture, prior mood, time-on-task, and publication type after adjusting for multiple comparisons. There was provisional evidence that age moderated the effect of the manipulations on intrinsic motivation, such that larger effects were revealed for children compared to older learners. Altogether, anthropomorphisms/colors appear to be useful design principles.

Abstract. Material re-exposure (e.g., re-reading) is a popular mnemonic strategy, however, its utility has been questioned. We extend research on re-reading to re-watching – an emerging mnemonic technique given the increased use of recorded lectures today (e.g., in online courses). Consistent with findings from recent investigations of re-reading, there were no benefits of massed re-watching on memory for lecture material and re-watching increased rates of mind wandering. We discuss implications for understanding the cognitive consequences of re-exposure-based mnemonics.

Item does not contain fulltext Physiological limitations on the visual system require gaze to move from location to location to extract the most relevant information within a scene. Therefore, gaze provides a real-time index of the information-processing priorities of the visual system. We investigated gaze allocation during mind wandering (MW), a state where cognitive priorities shift from processing task-relevant external stimuli (i.e., the visual world) to task-irrelevant internal thoughts. In both a main study and a replication, we recorded the eye movements of college-aged adults who studied images of urban scenes and responded to pseudorandom thought probes on whether they were mind wandering or attentively viewing at the time of the probe. Probe-caught MW was associated with fewer and longer fixations, greater fixation dispersion, and more frequent eyeblinks (only observed in the main study) relative to periods of attentive scene viewing. These findings demonstrate that gaze indices typically considered to represent greater engagement with scene processing (e.g., longer fixations) can also indicate MW. In this way, the current work exhibits a need for empirical investigations and computational models of gaze control to account for MW for a more accurate representation of the moment-to-moment information-processing priorities of the visual system.

Online education provides the opportunity to present lecture material to students in different formats or modalities, however there is debate about which lecture formats are best. Here, we conducted four experiments with 19–68 year old online participants to address the question of whether visuals of the instructor in online video lectures benefit learning. In Experiments 1 (N = 168) and 2 (N = 206) participants were presented with a lecture in one of three modalities (audio, audio with text, or audio with visuals of the instructor). Participants reported on their attentiveness – mind wandering (MW) – throughout the lecture and then completed a comprehension test. We found no evidence of an advantage for video lectures with visuals of the instructor in terms of a reduction in MW or increase in comprehension. In fact, we found evidence of a comprehension cost, suggesting that visuals of instructors in video lectures may act as a distractor. In Experiments 3 (N = 88) and 4 (N = 109) we explored learners' subjective evaluations of lecture formats across 4 different lecture formats (audio, text, audio + text, audio + instructor, audio + text + instructor). The results revealed learners not only find online lectures with visuals of the instructor more enjoyable and interesting, they believe this format most facilitates their learning. Taken together, these results suggest visuals of the instructor potentially impairs comprehension, but learners prefer and believe they learn most effectively with this format. We refer to as the Instructor Presence Effect and discuss implications for multimedia learning and instructional design.

Analyzing the quality of classroom talk is central to educational research and improvement efforts. In particular, the presence of authentic teacher questions, where answers are not predetermined by the teacher, helps constitute and serves as a marker of productive classroom discourse. Further, authentic questions can be cultivated to improve teaching effectiveness and consequently student achievement. Unfortunately, current methods to measure question authenticity do not scale because they rely on human observations or coding of teacher discourse. To address this challenge, we set out to use automatic speech recognition, natural language processing, and machine learning to train computers to detect authentic questions in real-world classrooms automatically. Our methods were iteratively refined using classroom audio and human-coded observational data from two sources: (a) a large archival database of text transcripts of 451 observations from 112 classrooms; and (b) a newly collected sample of 132 high-quality audio recordings from 27 classrooms, obtained under technical constraints that anticipate large-scale automated data collection and analysis. Correlations between human-coded and computer-coded authenticity at the classroom level were sufficiently high ( r = .602 for archival transcripts and .687 for audio recordings) to provide a valuable complement to human coding in research efforts.

Collaborative problem solving (CPS) is an essential skill for the 21st century workforce, but remains difficult to assess. Understanding how CPS skills affect CPS performance outcomes can inform CPS training, task design, feedback design, and automated assessment. We investigated CPS behaviors (individually and in co-occurring patterns) in 101 (N = 303) remote triads who collaboratively played an educational game called Physics Playground for 45-min. Team interactions consisting of open-ended speech occurring over video-conferencing with screen sharing. We coded participant's utterances relative to a CPS framework consisting of three facets (i.e., competencies such as constructing shared knowledge) manifested in 19 specific indicators (e.g., responds to other's questions/ideas). A matching technique was used to isolate the effect of CPS behaviors on CPS outcomes (quality of solution of a game level) controlling for pertinent covariates. Mixed-effects ordinal regression models indicated that proposing solution ideas and discussing results were the major predictors of CPS performance, and that team-member activities surrounding idea generation mattered. These findings highlighted the importance of both individual and collective contributions and social and cognitive skills in successful CPS outcomes.

Educational video games are hypothesized to be good environments for promoting learning; however, research on conceptual learning from games is mixed. We tested whether embedding a learning support in the form of short animations illustrating physics concepts that can be used to aid gameplay improved learning. Ninety-six 7th to 11th grade students were randomly assigned to play Physics Playground with or without the learning supports over a 4-day period. Results indicate that students who played a version of the game with embedded learning supports showed more improvement on a far- (d = 0.36), but not on a near-transfer physics assessment (d = 0.17) compared to those who played without the supports. The learning supports did not affect students’ enjoyment with the game. We conclude that the game-embedded animations were effective at promoting conceptual learning without sacrificing the fun of game-based learning.