The integration of mobile technology in education raises concerns about teachers’ work-life boundaries. Most studies examine boundary issues from a Western, individualistic perspective, prompting the question: How might work-life balance be understood within the context of a collectivist culture? This study examines how Chinese teachers manage boundaries on the all-in-one app WeChat. A survey of 108 teachers shows most view WeChat positively for work, while interviews with 18 teachers reveal that while teachers experience fatigue from blurred boundaries and constant availability, they also view WeChat as indispensable for managing fragmented responsibilities, sustaining relationships, and coordinating collective tasks. Teachers employ workarounds to negotiate expectations of accessibility. These practices highlight what we describe as expected permeability, a relationally constructed rhythm of accessibility shaped by obligations and tie-specific norms, while foregrounding relational agency as a stronger lens for rethinking both platform design and work-life balance theory beyond individualistic framings.

Online communities are increasingly important in forming and maintaining relationships but have also faced criticism for toxic or depression-inducing content. Motivated by research showing that grateful reflection can lead to enhanced well-being, this paper explores how we might design online communities centered on gratitude through a qualitative study with 15 participants. To elicit insights on how people view expressing gratitude in online communities, we built a simple gratitude-centered online community, Gratitude, designed to be similar in nature to many online communities, where users create short posts (notes of gratitude in response to prompts) that other members can browse, react to, and comment on. Participants were first interviewed and then used the Gratitude platform for three weeks, during which they filled out surveys after each prompt. We found that while participants had concerns or questions about the value of expressing gratitude publicly and the risks associated with doing so, they also described experiencing many benefits, such as providing one with a platform for sharing; inspiring reflection and positivity; fostering connection and empathy; and contributing to a cycle of gratitude and vulnerability. Participants raised several areas for design related to better support for interaction and connection, privacy and authenticity, and motivation and engagement. We conclude by discussing implications for future research on the design of prosocial online communities centering cycles of positivity and authentic individual reflection in communal interactions.

Surveys are a powerful tool for collecting data and eliciting insights on social phenomena, and are critical in product design, marketing, scientific research, and other domains. However, traditional open-ended and closed-ended question formats limit researchers' ability to capture data that combines both the richness of qualitative insights and the analytical rigor of quantitative data. Closed-ended questions facilitate structured data collection that is amenable to statistical analysis but limit respondents' answers. In contrast, open-ended questions allow for nuanced responses incorporating new perspectives but require significant effort to interpret due to their unstructured nature. Moreover, traditional survey tools lack mechanisms to prompt respondents for deeper reflections or to facilitate engagement with others' perspectives, limiting the potential for richer insights. To address these problems, we propose Dynamic Surveys, a survey platform that uses Large Language Models (LLMs) to dynamically cluster qualitative responses in real time and to elicit quantitative ratings and rankings on those clusters and qualitative reflections on how their views compare to broader respondent trends, especially helpful in early-stage or exploratory research settings. This process generates a report showing survey creators and respondents the clustered responses as well as each cluster's rank, rating distribution, and follow-up reflections. To evaluate Dynamic Surveys, we conducted two field studies with 93 participants over a 2-month period. In the first study, 52 students provided input for a career workshop, while in the second, 41 students gave feedback on gaps in their academic curriculum. Of these, 44 respondents filled out a survey on their experience using Dynamic Surveys. We also shared the generated report with 4 individuals who were interested in the insights for their work, and interviewed them to understand their perspectives on the results and any contextual risks they saw in the platform design. Our findings suggest that Dynamic Surveys not only provide richer and deeper insights into responses compared with traditional survey tools, but also increase engagement and foster a sense of community. We discuss broader implications for the design of survey platforms that blend qualitative depth with quantitative structure, facilitating richer insights and offering more collaborative interactions.

While mentorship offers many benefits, student access to mentorship is often limited. In this paper, we introduce Compass, a chat platform where industry professionals mentor large cohorts of 30+ students with the support of novel features that enable full engagement without the typical chaos of group chat. Specifically, we conceptualize conversations as composed of not only individual messages, but also multi-person conversational units that collapse large numbers of small but related conversational exchanges into single conceptual units in the main dialogue. Doing so makes it possible to preserve a coherent linear flow of conversation while also supporting non-linear conversational exchanges that can be concisely summarized computationally and built on in the main conversation. We report on design lessons learned over a year of small real-world studies culminating in a final deployment in which 2 industry professionals successfully mentored 30+ students over a 10-week period. We find that both mentors and mentees find the chat UI effective and sometimes preferable, and discuss broader implications for the design of chat UI for large group conversations.

With about 100 million people using it recently, SVCD(Smart Voice Controlled Device) are becoming demotic. Whether at home or in an office, usually, multiple appliances are under the control of a single SVCD and several people may manipulate an SVCD simultaneously. However, present SVCD fails to handle them appropriately. In this paper, we propose a novel framework for SVCD to eliminate orders’ ambiguity for single user or multi-user. We also design an algorithm combining Word2Vec and emotion detection for the device to wipe off ambiguity. Finally, we apply our framework into a virtual smart home scene and the performance of it indicates that our strategy resolves the problems commendably.

Teaching style plays an influential role in helping students to achieve academic success. In this paper, we explore a new problem of effectively understanding teachers' teaching styles. Specifically, we study 1) how to quantitatively characterize various teachers' teaching styles for various teachers and 2) how to model the subtle relationship between cross-media teaching related data (speech, facial expressions and body motions, content et al.) and teaching styles. Using the adjectives selected from more than 10,000 feedback questionnaires provided by an educational enterprise, a novel concept called Teaching Style Semantic Space (TSSS) is developed based on the pleasure-arousal dimensional theory to describe teaching styles quantitatively and comprehensively. Then a multi-task deep learning based model, Attention-based Multi-path Multi-task Deep Neural Network (AMMDNN), is proposed to accurately and robustly capture the internal correlations between cross-media features and TSSS. Based on the benchmark dataset, we further develop a comprehensive data set including 4,541 full-annotated cross-modality teaching classes. Our experimental results demonstrate that the proposed AMMDNN outperforms (+0.0842% in terms of the concordance correlation coefficient (CCC) on average) baseline methods. To further demonstrate the advantages of the proposed TSSS and our model, several interesting case studies are carried out, such as teaching styles comparison among different teachers and courses, and leveraging the proposed method for teaching quality analysis.

To give a more humanized response in Voice Dialogue Applications (VDAs), inferring emotion states from users’ queries may play an important role. However, in VDAs, we have tremendous amount of VDA users and massive scale of unlabeled data with high dimension features from multimodal information, which challenge the traditional speech emotion recognition methods. In this paper, to better infer emotion from conversational voice data, we proposed a semi-supervised multi-path generative neural network. Specifically, first, we build a novel supervised multi-path deep neural network framework. To avoid high dimensional input, raw features are trained by groups in local classifiers. Then high-level features of each local classifiers are concatenated as input of a global classifier. These two kinds classifiers are trained simultaneously through a single objective function to achieve a more effective and discriminative emotion inferring. To further solve the labeled-data-scarcity problem, we extend the multi-path deep neural network to a generative model based on semi-supervised variational autoencoder (semi-VAE), which is able to train the labeled and unlabeled data simultaneously. Experiment based on a 24,000 real-world dataset collected from Sogou Voice Assistant (SVAD13) and a benchmark dataset IEMOCAP show that our method significantly outperforms the existing state-of-the-art results.

There are many great works done in image generation. However, it is still an open problem how to generate a painting, which is meeting the aesthetic rules in specific style. Therefore, in this paper, we propose a demonstration to generate a specific painting based on users' input. In the system called AI Painting, we generate an original image from content text, transfer the image into a specific aesthetic effect, simulate the image into specific artistic genre, and illustrate the painting process.

The use of armatures is a convenient way of deforming and animating 3D digital models. However, interact with an armature is usually time-consuming, and often requires professional skills. Tangible interfaces, such as building blocks, while having improved the accessibility of digital construction, are still lacking in flexibility and present difficulties in dealing with curved armatures. This paper introduces TwistBlocks, a pluggable and twistable modular TUI that improves the accessibility of 3D modeling and animating by physical armature interaction. TwistBlocks is capable of creating complex armatures with dense branches, and supports a high DOF (Degree of Freedom) in physical manipulation. In addition, a set of software tools are provided for novice users to easily create, rig, and animate models. The global-posture sensing network sensing scheme can also measure the rotation and movement of the physical armature, and enables interaction between multiple models.