This survey describes recent progress in the field of Affective Computing (AC), with a focus on affect detection. Although many AC researchers have traditionally attempted to remain agnostic different emotion theories proposed by psychologists, affective technologies being developed are rife theoretical assumptions that impact their effectiveness. Hence, an informed and integrated examination from multiple areas will need become part computing practice if truly effective real-world systems...

Many important learning tasks feel uninteresting and tedious to learners. This research proposed that promoting a prosocial, self-transcendent purpose could improve academic self-regulation on such tasks. proposal was supported in 4 studies with over 2,000 adolescents young adults. Study 1 documented correlation between for self-reported trait measures of self-regulation. Those more also persisted longer boring task rather than giving tempting alternative and, many months later, were less...

Here, we consider the possibility of enabling AutoTutor, an intelligent tutoring system, to process learners' affective and cognitive states. AutoTutor is a fully automated computer tutor that simulates human tutors converses with students in natural language.

We present AutoTutor and Affective as examples of innovative 21 st century interactive intelligent systems that promote learning engagement. is an tutoring system helps students compose explanations difficult concepts in Newtonian physics enhances computer literacy critical thinking by interacting with them natural language adaptive dialog moves similar to those human tutors. constructs a cognitive model students' knowledge levels analyzing the text their typed or spoken responses its...

It is generally acknowledged that engagement plays a critical role in learning. Unfortunately, the study of has been stymied by lack valid and efficient measures. We introduce advanced, analytic, automated (AAA) approach to measure at fine-grained temporal resolutions. The AAA measurement grounded embodied theories cognition affect, which advocate close coupling between thought action. uses machine-learned computational models automatically infer mental states associated with (e.g.,...

We explored how computer vision techniques can be used to detect engagement while students (N = 22) completed a structured writing activity (draft-feedback-review) similar activities encountered in educational settings. Students provided annotations both concurrently during the and retrospectively from videos of their faces after activity. extract three sets features videos, heart rate, Animation Units (from Microsoft Kinect Face Tracker), local binary patterns orthogonal planes (LBP-TOP)....

The last decade has witnessed considerable interest in the investigation of affective dimensions learning and development advanced technologies that automatically detect respond to student affect. Identifying states students experience technology-enhanced contexts is a fundamental question this area. This article provides an initial attempt answer with selective meta-analysis 24 studies utilized mixture methodologies (online self-reports, online observations, emote-aloud protocols, cued...

<?Pub Dtl=""?> We describe a cognitive architecture learning intelligent distribution agent (LIDA) that affords attention, action selection and human-like intended for use in controlling agents replicate human experiments as well performing real-world tasks. LIDA combines sophisticated selection, motivation via emotions, centrally important attention mechanism, multimodal instructionalist selectionist learning. Empirically grounded science neuroscience, the employs variety of modules...

We investigated the temporal dynamics of students' cognitive-affective states (confusion, frustration, boredom, engagement/flow, delight, and surprise) during deep learning activities. After a session with an intelligent tutoring system conversational dialogue, learner were classified by learner, peer, two trained judges at approximately 100 points in tutorial session. Decay rates for estimated fitting exponential curves to time series affect responses. The results partially confirmed...

Source Code Summarization is an emerging technology for automatically generating brief descriptions of code. Current summarization techniques work by selecting a subset the statements and keywords from code, then including information those in summary. The quality summary depends heavily on process subset: high-quality selection would contain same that programmer choose. Unfortunately, little evidence exists about programmers view as important when they summarize source In this paper, we...

In an attempt to discover the facial action units for affective states that occur during complex learning, this study adopted emote-aloud procedure in which participants were recorded as they verbalised their while interacting with intelligent tutoring system (AutoTutor). Participants' expressions coded by two expert raters using Ekman's Facial Action Coding System and analysed association rule mining techniques. The received overall kappa ranged between .76 .84. analysis uncovered actions...

Affect detection is a key component in developing intelligent educational interfaces that are capable of responding to the affective needs students. In this paper, computer vision and machine learning techniques were used detect students' affect as they an game designed teach fundamental principles Newtonian physics. Data collected real-world environment school lab, which provides unique challenges for from facial expressions (primary channel) gross body movements (secondary - up thirty...

We explored the reliability of detecting learners' affect by monitoring their gross body language (body position and arousal) during interactions with an intelligent tutoring system called AutoTutor. Training validation data on affective states were collected in a learning session AutoTutor, after which (i.e., emotions) rated learner, peer, two trained judges. An automated pressure measurement was used to capture exerted learner seat back chair session. extracted sets features from maps. The...