Designing Conversational AI systems to support older adults requires these systems to explain their behavior in ways that align with older adults’ preferences and context. While prior work has emphasized the importance of AI explainability in building user trust, relatively little is known about older adults’ requirements and perceptions of AI-generated explanations. To address this gap, we conducted an exploratory Speed Dating study with 23 older adults to understand their responses to contextually grounded AI explanations. Our findings reveal the highly context-dependent nature of explanations, shaped by conversational cues such as the content, tone, and framing of explanation. We also found that explanations are often interpreted as interactive, multi-turn conversational exchanges with the AI, and can be helpful in calibrating urgency, guiding actionability, and providing insights into older adults’ daily lives for their family members. We conclude by discussing implications for designing context-sensitive and personalized explanations in Conversational AI systems.

While commercial conversational agents (CA) (i.e. Google assistant, Siri, Alexa) are widely used, these systems have limitations in error-handling, flexibility, personalization and overall dialogue management that are amplified in care coordination settings. In this paper, we synthesize and articulate these limitations through quantitative and qualitative analysis of 56 older adults interacting with a commercial CA deployed in their home for a 10 week period. We look at the CA as a compensatory technology in an older adult's care network. We argue that the CA limitations are rooted in the rigid cue-and-response style of task-oriented interactions common in CAs. We then propose a redesign for CA conversation flow to favor flexibility and personalization that is nonetheless viable within the limitations of current AI and machine learning technologies. We explore design tradeoffs to better support the usability needs of older adults compared to current design optimizations driven by efficiency and privacy goals.

Studies of time-continuous human behavioral phenomena often rely on ratings from multiple annotators. Since the ground truth of the target construct is often latent, the standard practice is to use ad-hoc metrics (such as averaging annotator ratings). Despite being easy to compute, such metrics may not provide accurate representations of the underlying construct. In this paper, we present a novel method for modeling multiple time series annotations over a continuous variable that computes the ground truth by modeling annotator specific distortions. We condition the ground truth on a set of features extracted from the data and further assume that the annotators provide their ratings as modification of the ground truth, with each annotator having specific distortion tendencies. We train the model using an Expectation-Maximization based algorithm and evaluate it on a study involving natural interaction between a child and a psychologist, to predict confidence ratings of the children's smiles. We compare and analyze the model against two baselines where: (i) the ground truth in considered to be framewise mean of ratings from various annotators and, (ii) each annotator is assumed to bear a distinct time delay in annotation and their annotations are aligned before computing the framewise mean.

We report on a nine-month-long observational study with teachers and students with autism in a classroom setting. We explore the impact of motion-based activities on students' behavior. In particular, we examine how the playful gaming activity impacted students' engagement, peer-directed social behaviors, and motor skills. We document the effectiveness of a collaborative game in supporting initiation of social activities between peers, and in eliciting novel body movements that students were not observed to produce outside of game play. We further identify the positive impact of game play on overall classroom engagement. This includes an "audience effect" whereby non-playing peers direct initiations to those playing the game and vice versa, and a positive "spillover" effect of the activity on students' social behavior outside of game play. We identify key considerations for designing and deploying motion-based activities for children with autism in a classroom setting.

Abstract Developmental psychology researchers examine the temporal relationships of social and communicative behaviors, such as how a child responds to a name call, to understand early typical and atypical development and to discover early signs of autism and developmental delay. These related behaviors occur together or within close temporal proximity, forming unique patterns and relationships of interest. However, the task of finding these early signs, which are in the form of atypical behavioral patterns, becomes more challenging when behaviors of multiple children at different ages need to be compared with each other in search of generalizable patterns. The ability to visually explore the temporal relationships of behaviors, including flexible redefinition of closeness, over multiple social interaction sessions with children of different ages, can make such knowledge extraction easier. We have designed a visualization tool called TipoVis that helps psychology researchers visually explore the temporal patterns of social and communicative behaviors. We present two case studies to show how TipoVis helped two researchers derive new understandings of their data.

The recent emergence of comfortable wearable sensors has focused almost entirely on monitoring physical activity, ignoring opportunities to monitor more subtle phenomena, such as the quality of social interactions. We argue that it is compelling to address whether physiological sensors can shed light on quality of social interactive behavior. This work leverages the use of a wearable electrodermal activity (EDA) sensor to recognize ease of engagement of children during a social interaction with an adult. In particular, we monitored 51 child-adult dyads in a semi-structured play interaction and used Support Vector Machines to automatically identify children who had been rated by the adult as more or less difficult to engage. We report on the classification value of several features extracted from the child's EDA responses, as well as several other features capturing the physiological synchrony between the child and the adult.

A child's failure to respond to his or her name being called is an early warning sign for autism and response to name is currently assessed as a part of standard autism screening and diagnostic tools. In this paper, we explore markerless child head tracking as an unobtrusive approach for automatically predicting child response to name. Head turns are used as a proxy for visual attention. We analyzed 50 recorded response to name sessions with the goal of predicting if children, ages 15 to 30 months, responded to name calls by turning to look at an examiner within a defined time interval. The child's head turn angles and hand annotated child name call intervals were extracted from each session. Human assisted tracking was employed using an overhead Kinect camera, and automated tracking was later employed using an additional forward facing camera as a proof-of-concept. We explore two distinct analytical approaches for predicting child responses, one relying on rule-based approached and another on random forest classification. In addition, we derive child response latency as a new measurement that could provide researchers and clinicians with finer grain quantitative information currently unavailable in the field due to human limitations. Finally we reflect on steps for adapting our system to work in less constrained natural settings.

Paralinguistic cues in children’s speech convey the child’s affective state and can serve as important markers for the early detection of autism spectrum disorder (ASD). In this paper, we detect paralinguistic events, such as laughter and fussing/crying, along with toddlers’ speech from the Multi-modal Dyadic Behavior Dataset (MMDB). We use both spectral and prosodic acoustic features selected using a combination of filter and wrapperbased methods. The classification accuracy using a support vector machine with a linear kernel for detecting laughter in children’s speech was 77.87% and that for fussing/crying was 79.37%. A tertiary classification scheme for detecting laughter, fussing/crying, and speech yielded an accuracy of 69.73%. To test for the generalization of the approach for detecting fussing/crying, we used recordings from the Strange Situation protocol, which is used to observe attachment behavior between an infant and a parent. Using a cross-corpus testing set for detecting fussing/crying, we obtained a detection accuracy of 71.6%. These results indicate that the selected acoustic features are capable of discriminating children’s laughter, fussing/crying, and speech and the algorithms generalize well to a dataset consisting of paralinguistic cues of a different age group, infants (12 18 months of age), gathered in a different context.

We introduce a new problem domain for activity recognition: the analysis of children's social and communicative behaviors based on video and audio data. We specifically target interactions between children aged 1-2 years and an adult. Such interactions arise naturally in the diagnosis and treatment of developmental disorders such as autism. We introduce a new publicly-available dataset containing over 160 sessions of a 3-5 minute child-adult interaction. In each session, the adult examiner followed a semi-structured play interaction protocol which was designed to elicit a broad range of social behaviors. We identify the key technical challenges in analyzing these behaviors, and describe methods for decoding the interactions. We present experimental results that demonstrate the potential of the dataset to drive interesting research questions, and show preliminary results for multi-modal activity recognition.

Laughter is an important para-linguistic cue that can be useful in gauging the affective state of the speaker. In this paper, we present an approach to detecting laughter in children’s speech using acoustic features in the spectral and prosodic domains. Feature selection was performed using the information gain-based technique and a speaker-independent validation using a support vector machine (SVM), an accuracy of 94.43% was observed, which was a 12.48% absolute improvement over the baseline result of 81.95%. For us to explore generalization properties, the models of speech and laughter were tested on a completely different database of adult-child interactions known as the Multimodal Dyadic Behavior Dataset (MDBD). The accuracy using the earlier trained models was 70.58%. Even though the children in this database were toddlers (less than three years old), the results suggest that the predictive power of the selected features generalizes well to different forms of children’s laughter.

Severe behavior problems of children with developmental disabilities often require intervention by specialists. These specialists rely on direct observation of the behavior, usually in a controlled clinical environment. In this paper, we present a technique for using on-body accelerometers to assist in automated classification of problem behavior during such direct observation. Using simulated data of episodes of severe behavior acted out by trained specialists, we demonstrate how machine learning techniques can be used to segment relevant behavioral episodes from a continuous sensor stream and to classify them into distinct categories of severe behavior (aggression, disruption, and self-injury). We further validate our approach by demonstrating it produces no false positives when applied to a publicly accessible dataset of activities of daily living. Finally, we show promising classification results when our sensing and analysis system is applied to data from a real assessment session conducted with a child exhibiting problem behaviors.

We describe a system for detecting moments of eye contact between an adult and a child, based on a single pair of gaze-tracking glasses which are worn by the adult. Our method utilizes commercial gaze tracking technology to determine the adult's point of gaze, and combines this with computer vision analysis of video of the child's face to determine their gaze direction. Eye contact is then detected as the event of simultaneous, mutual looking at faces by the dyad. We report encouraging findings from an initial implementation and evaluation of this approach.