Healthcare professionals (HCPs) face increasing occupational stress and burnout. Supporting HCPs’ need for relatedness is fundamental to their psychological wellbeing and resilience. However, how technologies could support HCPs’ relatedness in the workplace remains less explored. This study incorporated semi-structured interviews (n = 15) and co-design workshops (n = 21) with HCPs working in the UK National Health Service (NHS), to explore their current practices and preferences for workplace relatedness support, and how technology could be utilized to benefit relatedness. Qualitative analysis yielded a four-layer model of HCPs’ relatedness need, which includes Informal Interactions, Camaraderie and Bond, Community and Organizational Care, and Shared Identity. Workshops generated eight design concepts (e.g., Playful Encounter, Collocated Action, and Memories and Stories) that operationalize the four relatedness need layers. We conclude by highlighting the theoretical relevance, practical design implications, and the necessity to strengthen relatedness support for HCPs in the era of digitalization and artificial intelligence.

Abstract Self-determination theory (SDT) has been widely successful in human–computer interaction (HCI). It offers ready concepts, measures, and theoretical propositions for third wave HCI topics such as user experience, fun, wellbeing, motivation, or user autonomy. Still, HCI applications of SDT have been partial, at times superficial, and disconnecting—leaving great unfulfilled potential which motivated the present special issue. In this introduction, we present SDT to interested scholars, chart its use across HCI to date, and outline six advances to move HCI toward more intentional applications of SDT. As the articles from this issue illustrate, future growth areas of SDT in HCI are in extending domain-specific models and applications, harnessing underused parts of theory, computational formalization, extending levels of analysis, facilitating design translation, and engaging in a cross-disciplinary dialogue on autonomy.

Healthcare professionals (HCPs) face increasing levels of stress and burnout. Technological wellbeing interventions provide accessible and flexible support for HCPs. While most studies have focused on mobile- and web-based programs, alternative technologies like virtual reality (VR), augmented reality (AR), tangible interfaces, and embodied technologies are emerging as engaging and effective tools for wellbeing interventions. However, there is still a lack of research on how such technologies are perceived among HCPs. This study explored HCPs' perceptions and preferences for various types of wellbeing technologies, by conducting a 2-phase co-design study involving 26 HCPs in idea generation, concept evaluation, prototype testing, and design iteration. From our findings, HCPs highly valued the potential of technologies to support mental health with immersive, embodied, and collective experiences. Furthermore, we provided design recommendations for wellbeing technologies for HCPs that sustain user engagement by meeting their needs for autonomy, competence, and relatedness in the experiences.

Conversational agents (CAs) are rapidly advancing across industry and academia and it is crucial to consider the values embedded within these systems. Value-sensitive design practices have benefited AI-based systems, but have not yet been widely applied to CAs. This paper introduces the Value-Sensitive Conversational Agent (VSCA) Framework. The framework uses collaborative design (co-design) activities to guide CA creators and CA users to collaboratively create three key artefacts that elicit CA users’ values and are technically useful for CA creators to drive implementation forward, resulting in value embodied CA prototypes. The paper presents the practical framework and toolkit, followed by a mixed-method evaluation through design workshops, semi-structured interviews, and a comparative survey. Results show that the framework and toolkit increase CA creators’ value-sensitivity, empower CA users, enhance collaboration, and produce value-embodied prototypes. Based on this work, we offer 14 guidelines to practically support value sensitivity in CAs.

Asthma affects an estimated 334 million people worldwide, causing over 461 000 deaths. Exacerbations or asthma attacks can be predicted with new sensor technologies. We explore how recordings of human voice, and machine learning can provide better diagnostics for pulmonary diseases like asthma, as well as tools for helping patients better manage it. Past studies have focused on data collection processes that either mimic traditional auscultation, or make multi-sensor measurements, where the application of specialised recording hardware is required, possibly by expert personnel. This is costly and places limits on the size of the studies (e.g., number of study participants, and recording devices). In this paper, we consider another avenue, that of modelling self-recorded voice samples made using regular smartphones, along with self-reported clinical diagnosis annotations; specifically of asthma. We propose the usage of self-supervised learning that aims to reduce within-class representation redundancy among heterogeneous samples as an auxiliary task to promote robust, bias-free learning. The application of our method achieves an absolute increase of 1.80% in area under the Precision-Recall curve, compared to not using it, and a total of 3.54% compared to our baseline.

Monitoring and supporting daily routines in households with dementia is highly important. Here we analyse daily activity in 104 households with dementia across 24 months using passive motion sensors, door sensors and bed mat. We use Markov chain to extract the transitions around the house and we compare these transitions over time. We found that transitions around the house can be used to uniquely match the household as a distinctive fingerprint. We observed that the fingerprint of single-occupancy households is stronger than multiple occupancy and that predicting consecutive periods of time has a higher accuracy due to less change in routine. We focused the latter part of our study on the single occupancy households, specifically looking at the impact of the house floorplan. We observed that despite having similar or identical floorplans, the household fingerprint is still unique and related to the level of activity, and routine.

Understanding the relationship between technology and wellbeing is important in order to raise awareness and to improve interaction designs with digital technologies. Most studies used the time spent and frequency information of digital technology usage, very few explored the sequences and the patterns of how the activity occurs. We introduce the concept of “digital context,” a representation of activity data occurring in a short time-window. Using data from our study, we determined whether: (1) there are digital context patterns that are more frequent in a particular mood compared to other moods; and (2) in the case such patterns exist, whether they can be used to improve the performance of mood prediction models. Our results showed that a mood prediction model that include digital context features yielded an accuracy of 77.8%, which is an improvement compared with the models proposed in past studies.

Digital technology influences behaviours, moods and wellbeing. The relationships are complex, but users are increasingly interested in finding how to balance a digital life with psychological wellbeing. We present an approach for investigating the relationship between lifestyle aspects and digital technology usage patterns that combines MindGauge, a mobile app enabling users collect and analyse their moods and behaviours, with a productivity tool (RescueTime). We then report a 16-month study in which we collected computer and smartphone usage and self-reports from 72 participants. We present methods for analysing the relationship between productivity, task-switching, mood and lifestyle, and more specifically how digital technology usage associates with productivity and task-switching. Our study also investigates how lifestyle aspects (sleep quality, physical activity, workload, social interaction and alcoholic drink consumption) relate to mood, task-switching and productivity. Results show that more frequent task-switching is associated with negative moods. A few lifestyle aspects, such as sleep quality and physical activity, had a significant relationship with positive moods. We also contribute a mood detection model that utilise both digital footprints and lifestyle contexts, yielding an accuracy of 87 percent. The study provides evidence that such methods can be used to understand the impact of technology on wellbeing.

Joshua Y. Kim, Kalina Yacef, Greyson Kim, Chunfeng Liu, Rafael Calvo, Silas Taylor. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Recent research suggests that virtual reality (VR) games can engage players in physical activity with high levels of enjoyment. Understanding users’ motivation to engage and enjoy immersive VR exercise platforms is thus important to designers. We designed a VR exercise platform and conducted an experiment with two conditions, one with a static user interface (UI) and the other with an open world environment. Across participants there was significantly (p = 0.03*) greater enjoyment reported in an open world compared to static UI. Enjoyment in both static UI and open world conditions was positively correlated wih user’s psychological needs and experience; autonomy and immersion. Participants’ future play intention was also predicted by autonomy and immersion, but only within the open world condition. Our findings also suggest players can be classified into entertainment-focused and exercise-focused with different expectations and therefore different engagement behaviors with each VR exercise environment. The study highlights the value of informing VR design with measures of psychological need satisfaction.

Volunteering benefits those who receive and those who provide help. Yet barriers can inhibit engagement with and motivation for volunteering activities. Online environments on one hand help to lower some of these barriers, but on the other hand they can introduce new obstacles specially when the medium transforms the social interactions important to volunteers. We study the motivational drivers of online volunteering, and how those are affected by design. Specifically, we focus on relatedness as a source of motivation. We describe two studies with volunteers that help medical students to learn and improve their communication skills through mock interviews in an educational program. The volunteers can participate in the program face-to-face or through an online platform. The first study consisted of a survey (n = 66 volunteers), two workshops and one interview (n = 12 volunteers) in which we explored volunteer demographics, motivations, psychological needs, and experiences. Findings suggested relatedness can be an important indicator of volunteer motivations. In the second study, we added a feature to the online platform to display personal gratitude messages from student beneficiaries to the volunteers in order to improve the experience of relatedness between them. In total, n = 30 volunteers completed 196 sessions. We used survey and system data to assess the impact of gratitude on perceived relatedness, motivation, and behavior (immediate, booked, and completed appointments). Results showed that the expression of gratitude by the beneficiary significantly affected the volunteer’s experience of relatedness which then correlated with immediate appointments booking behavior by each volunteer. The implications for design of online volunteering systems are discussed.

Effective medical consultation requires good nonverbal communication between patients and doctors. Nonverbal behavior (NVB) mimicry, when a person imitates the NVB of the conversation partner, has been associated with building rapport between people. We study how NVB mimicry influences the quality of a medical consultation in a video conference. Computer vision algorithms were used to analyze 2027.75 minutes of recorded medical video consultations between medical students (N = 130) and volunteers who acted as Simulated Patients (SP, N = 29). We automatically detected students’ NVB mimicry to the SP and investigated the relationship between the NVB mimicry and students’ overall communication skills performance. The results highlighted the positive correlation between head nodding mimicry and assessed communication skills. In addition, we also identified NVB mimicry styles by cluster analysis and found that certain NVB mimicry styles have associated with better communication performance. These findings provide insights into the future design of systems that offer automatic feedback in communication skills training.

SUMMARY Exercise can improve health and well‐being. With this in mind, immersive virtual reality (VR) games are being developed to promote physical activity, and are generally evaluated through user studies. However, building such applications is time consuming and expensive. This paper introduces VR‐Rides, an object‐oriented application framework focused on the development of experiment‐oriented VR exergames. Following the modular programming pattern, this framework facilitates the integration of different hardware (such as VR devices, sensors, and physical activity devices) within immersive VR experiences that overlay game narratives on Google Street View panoramas. Combining software engineering and interaction patterns, modules of VR‐Rides can be easily added and managed in the Unity game engine. We evaluate the code efficiency and development effort across our VR exergames developed using VR‐Rides. The reliability, maintainability, and usability of our framework are also demonstrated via code metrics analysis and user studies. The results show that investing in a systematic approach to reusing code and design can be a worthwhile effort for researchers beyond software engineering.

Dimensional affect recognition is a challenging topic and current techniques do not yet provide the accuracy necessary for HCI applications. In this work we propose two new methods. The first is a novel self-organizing model that learns from similarity between features and affects. This method produces a graphical representation of the multidimensional data which may assist the expert analysis. The second method uses extreme learning machines, an emerging artificial neural network model. Aiming for minimum intrusiveness, we use only the heart rate variability, which can be recorded using a small set of sensors. The methods were validated with two datasets. The first is composed of 16 sessions with different participants and was used to evaluate the models in a classification task. The second one was the publicly available Remote Collaborative and Affective Interaction (RECOLA) dataset, which was used for dimensional affect estimation. The performance evaluation used the kappa score, unweighted average recall and the concordance correlation coefficient. The concordance coefficient on the RECOLA test partition was 0.421 in arousal and 0.321 in valence. Results show that our models outperform state-of-the-art models on the same data and provides new ways to analyze affective states.

There is an urgent need to understand how technology impacts psychological health. This is challenging because the relationship between digital behaviour, emotions and wellbeing is complex, individual, and ethically sensitive. This study describes a mood detection system which solely utilises digital usage data from a commercial digital usage tracker tool. Using 813 days of digital behaviour data, and 807 mood self-reports, from 47 users, the system achieved maximum accuracies varying between 81-82%. The result indicates that digital footprints are useful as features to detect mood. We discuss ethical issues, and an approach to address them.

Abstract Natural language processing (NLP) techniques can be used to make inferences about peoples’ mental states from what they write on Facebook, Twitter and other social media. These inferences can then be used to create online pathways to direct people to health information and assistance and also to generate personalized interventions. Regrettably, the computational methods used to collect, process and utilize online writing data, as well as the evaluations of these techniques, are still dispersed in the literature. This paper provides a taxonomy of data sources and techniques that have been used for mental health support and intervention. Specifically, we review how social media and other data sources have been used to detect emotions and identify people who may be in need of psychological assistance; the computational techniques used in labeling and diagnosis; and finally, we discuss ways to generate and personalize mental health interventions. The overarching aim of this scoping review is to highlight areas of research where NLP has been applied in the mental health literature and to help develop a common language that draws together the fields of mental health, human-computer interaction and NLP.

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 to activities encountered in educational settings. Students provided engagement annotations both concurrently during the writing activity and retrospectively from videos of their faces after the activity. We used computer vision techniques to extract three sets of features from videos, heart rate, Animation Units (from Microsoft Kinect Face Tracker), and local binary patterns in three orthogonal planes (LBP-TOP). These features were used in supervised learning for detection of concurrent and retrospective self-reported engagement. Area under the ROC Curve (AUC) was used to evaluate classifier accuracy using leave-several-students-out cross validation. We achieved an AUC = .758 for concurrent annotations and AUC = .733 for retrospective annotations. The Kinect Face Tracker features produced the best results among the individual channels, but the overall best results were found using a fusion of channels.

Experiencing high cognitive load during complex and demanding tasks results in performance reduction, stress, and errors. However, these could be prevented by a system capable of constantly monitoring users’ cognitive load fluctuations and adjusting its interactions accordingly. Physiological data and behaviors have been found to be suitable measures of cognitive load and are now available in many consumer devices. An advantage of these measures over subjective and performance-based methods is that they are captured in real time and implicitly while the user interacts with the system, which makes them suitable for real-world applications. On the other hand, emotion interference can change physiological responses and make accurate cognitive load measurement more challenging. In this work, we have studied six galvanic skin response (GSR) features in detection of four cognitive load levels with the interference of emotions. The data was derived from two arithmetic experiments and emotions were induced by displaying pleasant and unpleasant pictures in the background. Two types of classifiers were applied to detect cognitive load levels. Results from both studies indicate that the features explored can detect four and two cognitive load levels with high accuracy even under emotional changes. More specifically, rise duration and accumulative GSR are the common best features in all situations, having the highest accuracy especially in the presence of emotions.

Although content sharing provides many benefits, content owners lose full control of their content once they are given away. Existing solutions provide limited capabilities of content access control as they are vendor-specific, non-structured and non-flexible. In this paper, we present an open and flexible software solution called SelfProtect Object (SPO). SPO bundles content and policy files in an object that can protect its contents by itself anywhere and anytime. Our policy is based on XACML, a generic policy language allowing fine-grain access with rules and conditions. We also design and implement a prototype of SPO and demonstrate its capability through examples. Our solution is flexible to express a variety of access control rules and open to integrate into different applications on different platforms.

A main goal for learning analytics is to inform the design of a learning experience to improve its quality. The increasing presence of solutions based on big data has even questioned the validity of current scientific methods. Is this going to happen in the area of learning analytics? In this paper we postulate that if changes are driven solely by a digital footprint, there is a risk of focusing only on factors that are directly connected to numeric methods. However, if the changes are complemented with an understanding about how students approach their learning, the quality of the evidence used in the redesign is significantly increased. This reasoning is illustrated with a case study in which an initial set of activities for a first year engineering course were shaped based only on the student's digital footprint. These activities were significantly modified after collecting qualitative data about the students approach to learning. We conclude the paper arguing that the interpretation of the meaning of learning analytics is improved when combined with qualitative data which reveals how and why students engaged with the learning tasks in qualitatively different ways, which together provide a more informed basis for designing learning activities.

The trend towards Cloud computing infrastructure has increased the need for new methods that allow data owners to share their data with others securely taking into account the needs of multiple stakeholders. The data owner should be able to share confidential data while delegating much of the burden of access control management to the Cloud and trusted enterprises. The lack of such methods to enhance privacy and security may hinder the growth of cloud computing. In particular, there is a growing need to better manage security keys of data shared in the Cloud. BYOD provides a first step to enabling secure and efficient key management, however, the data owner cannot guarantee that the data consumers device itself is secure. Furthermore, in current methods the data owner cannot revoke a particular data consumer or group efficiently. In this paper, we address these issues by incorporating a hardware-based Trusted Platform Module (TPM) mechanism called the Trusted Extension Device (TED) together with our security model and protocol to allow stronger privacy of data compared to software-based security protocols. We demonstrate the concept of using TED for stronger protection and management of cryptographic keys and how our secure data sharing protocol will allow a data owner (e.g, author) to securely store data via untrusted Cloud services. Our work prevents keys to be stolen by outsiders and/or dishonest authorised consumers, thus making it particularly attractive to be implemented in a real-world scenario.

Cognitive load (CL) is experienced during critical tasks and also while engaged emotional states are induced either by the task itself or by extraneous experiences. Emotions irrelevant to the working memory representation may interfere with the processing of relevant tasks and can influence task performance and behavior, making the accurate detection of CL from nonverbal information challenging. This paper investigates automatic CL detection from facial features, physiology and task performance under affective interference. Data were collected from participants (n=20) solving mental arithmetic tasks with emotional stimuli in the background, and a combined classifier was used for detecting CL levels. Results indicate that the face modality for CL detection was more accurate under affective interference, whereas physiology and task performance were more accurate without the affective interference. Multimodal fusion improved detection accuracies, but it was less accurate under affective interferences. More specifically, the accuracy decreased with an increasing intensity of emotional arousal.

The authors first give a brief overview of how computers can afford multiple forms of transformational experiences. Some of these experiences can be purposely designed, for example, to detect and regulate students' affective states to improve aspects of their learning experiences. They can also be used in computer-based psychological interventions that treat psychological illness or that preventively promote wellbeing, healthy lifestyles, and mental health. This special section aims to contribute ideas, methods and case studies for how affective computing can move toward the goal of promoting wellbeing. The papers spread across some of the multiple modalities and techniques used to perceive and detect affect from text, physiology facial expressions, and gaze, and some of the approaches to analyze the expression of sentiments shared via online communities by depressed patients. The articles in this special section discuss how information that computers collect about our behaviour, cognition - and particularly affect - can be used in the further understanding, nurturing or development of wellbeing and human strengths: e.g. self-understanding, empathy, intrinsic motivation toward wellbeing healthy lifestyles.

Unobtrusive, contactless recordings of physiological signals are very important for many health and human-computer interaction applications. Most current systems require sensors which intrusively touch the user's skin. Recent advances in contact-free physiological signals open the door to many new types of applications. This technology promises to measure heart rate (HR) and respiration using video only. The effectiveness of this technology, its limitations, and ways of overcoming them deserves particular attention. In this paper, we evaluate this technique for measuring HR in a controlled situation, in a naturalistic computer interaction session, and in an exercise situation. For comparison, HR was measured simultaneously using an electrocardiography device during all sessions. The results replicated the published results in controlled situations, but show that they cannot yet be considered as a valid measure of HR in naturalistic human-computer interaction. We propose a machine learning approach to improve the accuracy of HR detection in naturalistic measurements. The results demonstrate that the root mean squared error is reduced from 43.76 to 3.64 beats/min using the proposed method.

Learning analytic techniques are allowing the observation of complex learning activities that were hidden until now. Writing is a task in which behavioral patterns can be observed to measure the level of engagement. Previous studies relied mostly on data collected by observers. In this paper Tracer, a novel learning analytic system to visualize behavioral patterns of students while writing and measuring engagement is described. The tool combines and analyzes the information obtained from document revisions and Website logs while students work in a writing assignment and provides visualizations and measurements for the level of engagement. A user study was conducted in a software engineering course where students wrote and submitted a project proposal using Google Docs. Tracer generated a graphical view of the gauged engagement, and an engagement time for each student. The obtained results show that the engagement time gauged by Tracer was moderately correlated to those reported by the students.

Affect detection from physiological signals has received a great deal of attention recently. One arising challenge is that physiological measures are expected to exhibit considerable variations or non-stationarities over multiple days/sessions recordings. These variations pose challenges to effectively classify affective sates from future physiological data. The present study collects affective physiological data (electrocardiogram (ECG), electromyogram (EMG), skin conductivity (SC), and respiration (RSP)) from four participants over five sessions each. The study provides insights on how diagnostic physiological features of affect change over time. We compare the classification performance of two feature sets, pooled features (obtained from pooled day data) and day-specific features using an up datable classifier ensemble algorithm. The study also provides an analysis on the performance of individual physiological channels for affect detection. Our results show that using pooled feature set for affect detection is more accurate than using day-specific features. The corrugator and zygomatic facial EMGs were more reliable measures for detecting valence than arousal compared to ECG, RSP and SC over the span of multi-session recordings. It is also found that corrugator EMG features and a fusion of features from all physiological channels have the highest affect detection accuracy for both valence and arousal.

The use of cloud computing writing tools, such as Google Docs, by students to write collaboratively provides unprecedented data about the progress of writing. This data can be exploited to gain insights on how learners' collaborative activities, ideas and concepts are developed during the process of writing. Ultimately, it can also be used to provide support to improve the quality of the written documents and the writing skills of learners involved. In this paper, we propose three visualisation approaches and their underlying techniques for analysing writing processes used in a document written by a group of authors: (1) the revision map, which summarises the text edits made at the paragraph level, over the time of writing. (2) the topic evolution chart, which uses probabilistic topic models, especially Latent Dirichlet Allocation (LDA) and its extension, DiffLDA, to extract topics and follow their evolution during the writing process. (3) the topic-based collaboration network, which allows a deeper analysis of topics in relation to author contribution and collaboration, using our novel algorithm DiffATM in conjunction with a DiffLDA-related technique. These models are evaluated to examine whether these automatically discovered topics accurately describe the evolution of writing processes. We illustrate how these visualisations are used with real documents written by groups of graduate students.

Text often expresses the writer's emotional state or evokes emotions in the reader. The nature of emotional phenomena like reading and writing can be interpreted in different ways and represented with different computational models. Affective computing (AC) researchers often use a categorical model in which text data are associated with emotional labels. We introduce a new way of using normative databases as a way of processing text with a dimensional model and compare it with different categorical approaches. The approach is evaluated using four data sets of texts reflecting different emotional phenomena. An emotional thesaurus and a bag‐of‐words model are used to generate vectors for each pseudo‐document, then for the categorical models three dimensionality reduction techniques are evaluated: Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (PLSA), and Non‐negative Matrix Factorization (NMF). For the dimensional model a normative database is used to produce three‐dimensional vectors (valence, arousal, dominance) for each pseudo‐document. This three‐dimensional model can be used to generate psychologically driven visualizations. Both models can be used for affect detection based on distances amongst categories and pseudo‐documents. Experiments show that the categorical model using NMF and the dimensional model tend to perform best.

Significant progress has been made in automatic facial expression recognition, yet most state of the art approaches produce significantly better reliabilities on acted expressions than on natural ones. User interfaces that use facial expressions to understand user's affective states need to be most accurate during naturalistic interactions. This paper presents a study where head movement features are used to recognize naturalistic expressions of affect. The International Affective Picture System (IAPS) collection was used as stimulus for triggering different affective states. Machine learning techniques are applied to classify user's expressions based on their head position and skin color changes. The proposed approach shows a reasonable accuracy in detecting three levels of valence and arousal for user-dependent model during naturalistic human-computer interaction.

Research towards automated feedback can build on the work in other areas. In this paper we explore question generation techniques. Most research in question generation has focused on generating content specific questions that help students comprehend a set of documents that they must read. However, this approach is not so useful in writing activities, as students would generally understand the document that they themselves wrote. The aim of our project is to build a system which automatically generates feedback questions for academic writing support, particularly for critical review support. This paper presents our question generation system which relies on both syntax-based and template-based approaches, and uses Wikipedia as background knowledge.

The Internet has been encouraging and enabling business collaborations via online transactions over the Web. However, managing transactions in a long-running business process across domains still remains a challenge. In this paper, we propose a novel financial-compensation-based transaction management model, fcBTxM, to address this challenge. Unlike classical transaction management, fcBTxM does not attempt to recover data consistency via rollback when a failure occurs. Instead, our model always tries to forward-roll a business process via financial compensation. We use a state machine to capture and describe the states of our transaction model and their relationships. We also develop a set of technologies and protocols for enabling the new transaction management. A real business collaboration example is used to demonstrate the concept, and preliminary testing results are provided to evaluate our technologies.

The automated detection of emotions opens the possibility to new applications in areas such as education, mental health and entertainment. There is an increasing interest on detection techniques that combine multiple modalities. In this study, we introduce automated techniques to detect users' affective states from a fusion model of facial videos and physiological measures. The natural behavior expressed on faces and their physiological responses were recorded from subjects (N=20) while they viewed images from the International Affective Picture System (IAPS). This paper provides a direct comparison between user-dependent, gender-specific, and combined-subject models for affect classification. The analysis indicates that the accuracy of the fusion model (head movement, facial color, and physiology) was statistically higher than the best individual modality for spontaneous affect expressions.

Signals from peripheral physiology (e.g., ECG, EMG, and GSR) in conjunction with machine learning techniques can be used for the automatic detection of affective states. The affect detector can be user-independent, where it is expected to generalize to novel users, or user-dependent, where it is tailored to a specific user. Previous studies have reported some success in detecting affect from physiological signals, but much of the work has focused on induced affect or acted expressions instead of contextually constrained spontaneous expressions of affect. This study addresses these issues by developing and evaluating user-independent and user-dependent physiology-based detectors of nonbasic affective states (e.g., boredom, confusion, curiosity) that were trained and validated on naturalistic data collected during interactions between 27 students and AutoTutor, an intelligent tutoring system with conversational dialogues. There is also no consensus on which techniques (i.e., feature selection or classification methods) work best for this type of data. Therefore, this study also evaluates the efficacy of affect detection using a host of feature selection and classification techniques on three physiological signals (ECG, EMG, and GSR) and their combinations. Two feature selection methods and nine classifiers were applied to the problem of recognizing eight affective states (boredom, confusion, curiosity, delight, flow/-engagement, surprise, and neutral). The results indicated that the user-independent modeling approach was not feasible; however, a mean kappa score of 0.25 was obtained for user-dependent models that discriminated among the most frequent emotions. The results also indicated that k-nearest neighbor and Linear Bayes Normal Classifier (LBNC) classifiers yielded the best affect detection rates. Single channel ECG, EMG, and GSR and three-channel multimodal models were generally more diagnostic than two--channel models.

Learning about subject matter and about writing by collaboratively authoring an electronic document is an important variant of computer-supported collaborative learning. Collaborative writing is particularly often practiced in Higher Education. Our research has the goal to develop comprehensive software support tools for collaborative discipline-based writing, and to study how the team writing process is affected by the use of these tools. This paper describes initial tool developments that integrate computational document analysis methods with process mining methods into a comprehensive writing environment and reports first experiences gained in a undergraduate engineering course.

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 to the different emotion theories proposed by psychologists, the affective technologies being developed are rife with theoretical assumptions that impact their effectiveness. Hence, an informed and integrated examination of emotion theories from multiple areas will need to become part of computing practice if truly effective real-world systems are to be achieved. This survey discusses theoretical perspectives that view emotions as expressions, embodiments, outcomes of cognitive appraisal, social constructs, products of neural circuitry, and psychological interpretations of basic feelings. It provides meta-analyses on existing reviews of affect detection systems that focus on traditional affect detection modalities like physiology, face, and voice, and also reviews emerging research on more novel channels such as text, body language, and complex multimodal systems. This survey explicitly explores the multidisciplinary foundation that underlies all AC applications by describing how AC researchers have incorporated psychological theories of emotion and how these theories affect research questions, methods, results, and their interpretations. In this way, models and methods can be compared, and emerging insights from various disciplines can be more expertly integrated.

Many approaches have been proposed for providing feedback in academic writing, however, few of them are visually based. We describe a novel visualisation method for providing feedback to support formative essay assessment. The visualisation method makes use of text mining techniques to provide insight on the semantics of the topics in an essay. We propose that visualisation can be used to mitigate many of the problems associated with the subjectivity of formative essay assessment. The visualisation method involves a process of non-negative matrix factorisation (NMF), to uncover topics in an essay, followed by multidimensional scaling, to map the essay topics to a 2-dimensional representation. We evaluate our approach with a subset of the British Academic Written English corpus of 2761 assignments written by university students.

In this paper we aim to bring together research in affective computing and educational design. We review the literature and describe the design of a methodological and technical framework for studying pedagogical designs that are informed by the affective state of learners. The proposed framework integrates techniques for affect recognition using physiology and text, and describes an approach to studying the affective dynamics of collaborative activities. We aim for this exploratory work to improve our understanding of how to best design group learning activities, and then to communicate these outcomes in the form of educational design patterns.

In this paper, we describe a novel visualization to support formative assessment in academic writing. The visualization makes use of text mining techniques to provide insight on the flow of topics in an essay. We propose that visualization can be used to mitigate many of problems associated with the subjectivity of essay assessment by bringing greater insight to an essaypsilas latent features. The proposed visualization method involves a process of non-negative matrix factorization (NMF), to uncover topics in an essay, follow by multidimensional scaling (MDS), to map the topic closeness of the essaypsilas paragraphs. We evaluate the visualization method with a corpus of 44 short essays written by university students.

This paper presents a new approach for automatic concept extraction, using grammatical parsers and Latent Semantic Analysis. The methodology is described, also the tool used to build the benchmarking corpus. The results obtained on student essays shows good inter-rater agreement and promising machine extraction performance. Concept extraction is the first step to automatically extract concept maps from studentpsilas essays or Concept Map Mining.

Over recent decades, concept mapping has been used as a valuable learning and teaching tool. Several types of scoring methods for concept map based assessment have been developed. In this paper, we describe the development of an automatic scoring framework that implements those techniques. We contribute a design that uses semantic Web technologies for both the management and the scoring of the concept maps.

We describe Glosser, a system that supports students in writing essays by 1) scaffolding their reflection with trigger questions, and 2) using text mining techniques to provide content clues that can help answer those questions. A comparison with other computer generated feedback and scorings systems is provided to explain the novelty of the approach. We evaluate the system with Wiki pages produced by postgraduate students as part of their assessment.

A fast and simple algorithm for approximately calculating the principal components (PCs) of a dataset and so reducing its dimensionality is described. This Simple Principal Components Analysis (SPCA) method was used for dimensionality reduction of two high-dimensional image databases, one of handwritten digits and one of handwritten Japanese characters. It was tested and compared with other techniques. On both databases SPCA shows a fast convergence rate compared with other methods and robustness to the reordering of the samples.