Creating webpages requires generating content and arranging layout while iteratively refining both to achieve a coherent design, a process that can be challenging for blind individuals. To understand how blind designers navigate this process, we conducted two rounds of co-design sessions with blind participants, using design probes to elicit their strategies and support needs. Our findings reveal a preference for content and layout to co-evolve, but this process requires external support through cues that situate local elements within the broader page structure as well as multimodal interactions. Building on these insights, we developed TangibleSite, an accessible web design tool that provides real-time multimodal feedback through tangible, auditory, and speech-based interactions. TangibleSite enables blind individuals to create, edit, and reposition webpage elements while integrating content and layout decisions. A formative evaluation with six blind participants demonstrated that TangibleSite enabled independent webpage creation, supported refinement across content and layout, and reduced barriers to achieving visually consistent designs.

Recent discussions at the intersection of journalism, HCI, and human-centered computing ask how technologies can help create reader-oriented news experiences. The current paper takes up this initiative by focusing on immigrant readers, a group who reports significant difficulties engaging with mainstream news yet has received limited attention in prior research. We report findings from our co-design research with eleven immigrant readers living in the United States and seven journalists working in the same region, aiming to enhance the news experience of the former. Data collected from all participants revealed an “unaddressed-or-unaccountable” paradox that challenges value alignment across immigrant readers and journalists. This paradox points to four metaphors regarding how conversational AI agents can be designed to assist news reading. Each metaphor requires conversational AI, journalists, and immigrant readers to coordinate their shared responsibilities in a distinct manner. These findings provide insights into reader-oriented news experiences with AI in the loop.

Understanding collaborative writing dynamics between native speakers (NS) and non-native speakers (NNS) is critical for enhancing collaboration quality and team inclusivity. In this paper, we partnered with communication researchers to develop visual analytics solutions for comparing NS and NNS behaviors in 162 writing sessions across 27 teams. The primary challenges in analyzing writing behaviors are data complexity and the uncertainties introduced by automated methods. In response, we present \textsc{COALA}, a novel visual analytics tool that improves model interpretability by displaying uncertainties in author clusters, generating behavior summaries using large language models, and visualizing writing-related actions at multiple granularities. We validated the effectiveness of \textsc{COALA} through user studies with domain experts (N=2+2) and researchers with relevant experience (N=8). We present the insights discovered by participants using \textsc{COALA}, suggest features for future AI-assisted collaborative writing tools, and discuss the broader implications for analyzing collaborative processes beyond writing.

News reading helps individuals stay informed about events and developments in society. Local residents and new immigrants often approach the same news differently, prompting the question of how technology, such as LLM-powered chatbots, can best enhance a reader-oriented news experience. The current paper presents an empirical study involving 144 participants from three groups in Virginia, United States: local residents born and raised there (N=48), Chinese immigrants (N=48), and Vietnamese immigrants (N=48). All participants read local housing news with the assistance of the Copilot chatbot. We collected data on each participant's Q&A interactions with the chatbot, along with their takeaways from news reading. While engaging with the news content, participants in both immigrant groups asked the chatbot fewer analytical questions than the local group. They also demonstrated a greater tendency to rely on the chatbot when formulating practical takeaways. These findings offer insights into technology design that aims to serve diverse news readers.

Marine Carpuat, Omri Asscher, Kalika Bali, Luisa Bentivogli, Fred Blain, Lynne Bowker, Monojit Choudhury, Hal Daumé Iii, Kevin Duh, Ge Gao, Alvin C Grissom II, Marzena Karpinska, Elaine C Khoong, William D. Lewis, Andre Martins, Mary Nurminen, Douglas W. Oard, Maja Popovic, Michel Simard, François Yvon. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Yimin Xiao, Yongle Zhang, Dayeon Ki, Calvin Bao, Marianna J. Martindale, Charlotte Vaughn, Ge Gao, Marine Carpuat. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Wearable technology has significantly improved the quality of life for older adults, and the emergence of on-body, movable robots presents new opportunities to further enhance well-being. Yet, the interaction design for these robots remains under-explored, particularly from the perspective of older adults. We present findings from a two-phase co-design process involving 13 older adults to uncover design principles for on-body robots for this population. We identify a rich spectrum of potential applications and characterize a design space to inform how on-body robots should be built for older adults. Our findings highlight the importance of considering factors like co-presence, embodiment, and multi-modal communication. Our work offers design insights to facilitate the integration of on-body robots into daily life and underscores the value of involving older adults in the co-design process to promote usability and acceptance of emerging wearable robotic technologies.

Recent advances in multimodal Human-Robot Interaction (HRI) datasets emphasize the integration of speech and gestures, allowing robots to absorb explicit knowledge and tacit understanding. However, existing datasets primarily focus on elementary tasks like object pointing and pushing, limiting their applicability to complex domains. They prioritize simpler human command data but place less emphasis on training robots to correctly interpret tasks and respond appropriately. To address these gaps, we present the NatSGLD dataset, which was collected using a Wizard of Oz (WoZ) method, where participants interacted with a robot they believed to be autonomous. NatSGLD records humans' multimodal commands (speech and gestures), each paired with a demonstration trajectory and a Linear Temporal Logic (LTL) formula that provides a ground-truth interpretation of the commanded tasks. This dataset serves as a foundational resource for research at the intersection of HRI and machine learning. By providing multimodal inputs and detailed annotations, NatSGLD enables exploration in areas such as multimodal instruction following, plan recognition, and human-advisable reinforcement learning from demonstrations. We release the dataset and code under the MIT License at https://www.snehesh.com/natsgld/to support future HRI research.

Emojis, which encapsulate semantics beyond words or phrases, have become prevalent in social network communications. This has spurred increasing scholarly interest in exploring their attributes and functionalities. However, emoji-related research and application face two primary challenges. First, researchers typically rely on crowd-sourcing to annotate emojis in order to understand their sentiments, usage intentions, and semantic meanings. Second, subjective interpretations by users can often lead to misunderstandings of emojis and cause a communication barrier. Large Language Models (LLMs) have achieved significant success in various annotation tasks, with ChatGPT demonstrating expertise across multiple domains. In our study, we assess ChatGPT's effectiveness in handling previously emoji-annotated and downstream tasks. Our objective is to validate the hypothesis that ChatGPT can serve as an alternative to human annotators in emoji research and that its ability to explain emoji meanings can enhance clarity and transparency in online communications. Our findings indicate that ChatGPT has extensive knowledge of emojis. It is adept at explaining the meaning of emojis across various application scenarios and demonstrates the potential to replace human annotators in a range of tasks.

Opportunistic interactions-the unstructured exchanges that emerge as individuals become aware of each other's presence-are essential for relationship building and information sharing in everyday life. Yet, fostering effective opportunistic interactions has proven challenging, especially at professional events that have increasingly transitioned from in person to online formats. In the current paper, we offer an in-depth qualitative account of how people initiate opportunistic interactions in social VR. Our participants consisted of 16 individuals with ongoing experience attending VR-mediated events in their professional communities. We conducted extensive observations with each participant during one or more events they attended. We also interviewed them after every observed event, obtaining self-reflections on their attempts to navigate opportunistic interactions with others. Our analysis revealed that participants sought to understand the extent to which social VR preserved the real-world meanings of various nonverbal cues, which we refer to as verisimilitude. We detailed the unique connections between a person's perceived verisimilitude and their social behaviors at each of the three steps toward initiating opportunistic interactions: availability recognition, attention capture, and ice-breaking. Across these steps, the VR platform typically replaces complex social mechanisms with feasible technical ones in order to function, thereby altering the preconditions necessary for a nonverbal cue's social meanings to remain intact. We identified a rich set of strategies that participants developed to assess verisimilitude and act upon it, while also confirming a lack of systematic knowledge guiding their practices. Based on these findings, we provide actionable insights for social VR platform design that can best support the initiation of opportunistic interactions for professional purposes.

While videoconferencing is a promising technology, it may present unique challenges and barriers for older adults with cognitive concerns. This paper presents a deconstructed view of videoconferencing technology use using a sociological dramaturgical framework developed by Erving Goffman. Our study recruited 17 older adults with varying cognitive concerns, employing technology discussion groups, interviews, and observations to gather data. Through a reflexive thematic analysis, we explore videoconferencing use among older adults with cognitive concerns, focusing on three major areas: the "performances and roles" where users adapt to new roles through videoconferencing; the "backstage," which involves the physical and logistical setup; and the "frontstage," where people communicate through audio and visual channels to present a desired impression. Our discussion generates insights into how deconstructing these elements can inform more meaningful and accessible HCI design.

Everyone spends some time waiting every day. HCI research has developed tools for boosting productivity while waiting. However, little is known about how people naturally spend their waiting time. We conducted an experience sampling study with 21 working adults who used a mobile app to report their daily waiting time activities over two weeks. The aim of this study is to understand the activities people do while waiting and the effect of situational factors. We found that participants spent about 60% of their waiting time on leisure activities, 20% on productive activities, and 20% on maintenance activities. These choices are sensitive to situational factors, including accessible device, location, and certain routines of the day. Our study complements previous ones by demonstrating that people purpose waiting time for various goals beyond productivity and to maintain work-life balance. Our findings shed light on future empirical research and system design for time management.

Although remote working is increasingly adopted during the pandemic, many are concerned by the low-efficiency in the remote working. Missing in text-based communication are non-verbal cues such as facial expressions and body language, which hinders the effective communication and negatively impacts the work outcomes. Prevalent on social media platforms, emojis, as alternative non-verbal cues, are gaining popularity in the virtual workspaces well. In this paper, we study how emoji usage influences developer participation and issue resolution in virtual workspaces. To this end, we collect GitHub issues for a one-year period and apply causal inference techniques to measure the causal effect of emojis on the outcome of issues, controlling for confounders such as issue content, repository, and author information. We find that emojis can significantly reduce the resolution time of issues and attract more user participation. We also compare the heterogeneous effect on different types of issues. These findings deepen our understanding of the developer communities, and they provide design implications on how to facilitate interactions and broaden developer participation.

Content creation today often takes place via collaborative writing. A longstanding interest of CSCW research lies in understanding and promoting the coordination between co-writers. However, little attention has been paid to individuals who write in their non-native language and to co-writer groups involving them. We present a mixed-method study that fills the above gap. Our participants included 32 co-writer groups, each consisting of one native speaker (NS) of English and one non-native speaker (NNS) with limited proficiency. They performed collaborative writing adopting two different workflows: half of the groups began with NNSs taking the first editing turn and half had NNSs act after NSs. Our data revealed a 'late-mover disadvantage' exclusively experienced by NNSs: an NNS's ideational contributions to the joint document were suppressed when their editing turn was placed after an NS's turn, as opposed to ahead of it. Surprisingly, editing help provided by AI-powered tools did not exempt NNSs from being disadvantaged. Instead, it triggered NSs' overestimation of NNSs' English proficiency and agency displayed in the writing, introducing unintended tensions into the collaboration. These findings shed light on the fair assessment and effective promotion of a co-writer's contributions in language diverse settings. In particular, they underscore the necessity of disentangling contributions made to the ideational, expressional, and lexical aspects of the joint writing.

Self-directed learning is becoming a significant skill for learners. However, learners may suffer from difficulties such as distractions, a lack of motivation, and so on. While self-tracking technologies have the potential to address these challenges, existing tools and systems mainly focused on tracking computer-based learning data in classroom contexts. Little is known about how students track and make sense of their learning data from non-classroom learning activities and which types of learning data are personally meaningful for learners. In this paper, we conducted a qualitative study with 24 users of Timing, a mobile learning tracking application in China. Our findings indicated that users tracked a variety of qualitative learning data (e.g., videos, photos of learning materials, and emotions) and made sense of this data using different strategies such as observing behavioral and contextual details in videos. We then provided implications for designing non-classroom and non-computer-based personal learning tracking tools.

A major challenge in the practical use of Machine Translation (MT) is that users lack guidance to make informed decisions about when to rely on outputs.Progress in quality estimation research provides techniques to automatically assess MT quality, but these techniques have primarily been evaluated in vitro by comparison against human judgments outside of a specific context of use.This paper evaluates quality estimation feedback in vivo with a human study simulating decision-making in high-stakes medical settings.Using Emergency Department discharge instructions, we study how interventions based on quality estimation versus backtranslation assist physicians in deciding whether to show MT outputs to a patient.We find that quality estimation improves appropriate reliance on MT, but backtranslation helps physicians detect more clinically harmful errors that QE alone often misses.

Academic writing in English can be challenging for non-native English speakers (NNESs). AI-powered rewriting tools can potentially improve NNESs’ writing outcomes at a low cost. However, whether and how NNESs make valid assessments of the revisions provided by these algorithmic recommendations remains unclear. We report a study where NNESs leverage an AI-powered rewriting tool, Langsmith, to polish their drafted academic essays. We examined the participants’ interactions with the tool via user studies and interviews. Our data reveal that most participants used Langsmith in combination with other tools, such as machine translation (MT), and those who used MT had different ways of understanding and evaluating Langsmith’s suggestions than those who did not. Based on these findings, we assert that NNESs’ quality assessment in AI-powered rewriting tools is influenced by the simultaneous use of multiple tools, offering valuable insights into the design of future rewriting tools for NNESs.

Many video sites or learning platforms allow real-time chatting or asynchronous commenting on specific time points during video lectures. Comments, as user-generated knowledge, facilitate social interaction but also affect cognitive learning. The visual layout of these comments can affect learners’ attention and learning, but the effect has rarely been studied. This study compares two common layouts (embedded vs. separated) and considers the content depth of comments through a laboratory eye-tracking experiment involving 40 participants. The results suggest that, with both layouts, learners switched attention to the comments every 10 seconds and stayed focused for 1.3 seconds on average before returning attention to the video. With an embedded layout, learners switched attention more frequently to the comments and remembered more surface-level comments. With a separate layout presenting deep-level comments, learners searched for information faster and performed better on open-book quizzes. We outline the design implications of using timeline-anchored comments to promote online learning.

Information seeking is crucial for people's self-care and wellbeing in times of public crises. Extensive research has investigated empirical understandings as well as technical solutions to facilitate information seeking by domestic citizens of affected regions. However, limited knowledge is established to support international migrants who need to survive a crisis in their host countries. The current paper presents an interview study with two cohorts of Chinese migrants living in Japan (N=14) and the United States (N=14). Participants reflected on their information seeking experiences during the COVID pandemic. The reflection was supplemented by two weeks of self-tracking where participants maintained records of their COVID-related information seeking practice. Our data indicated that participants often took language detours, or visits to Mandarin resources for information about the COVID outbreak in their host countries. They also made strategic use of the Mandarin information to perform selective reading, cross-checking, and contextualized interpretation of COVID-related information in Japanese or English. While such practices enhanced participants' perceived effectiveness of COVID-related information gathering and sensemaking, they disadvantaged people through sometimes incognizant ways. Further, participants lacked the awareness or preference to review migrant-oriented information that was issued by the host country's public authorities despite its availability. Building upon these findings, we discussed solutions to improve international migrants' COVID-related information seeking in their non-native language and cultural environment. We advocated inclusive crisis infrastructures that would engage people with diverse levels of local language fluency, information literacy, and experience in leveraging public services.

Global teams frequently consist of language-based subgroups who put together complementary information to achieve common goals. Previous research outlines a two-step work communication flow in these teams. There are team meetings using a required common language (i.e., English); in preparation for those meetings, people have subgroup conversations in their native languages. Work communication at team meetings is often less effective than in subgroup conversations. In the current study, we investigate the idea of leveraging machine translation (MT) to facilitate global team meetings. We hypothesize that exchanging subgroup conversation logs before a team meeting offers contextual information that benefits teamwork at the meeting. MT can translate these logs, which enables comprehension at a low cost. To test our hypothesis, we conducted a between-subjects experiment where twenty quartets of participants performed a personnel selection task. Each quartet included two English native speakers (NS) and two non-native speakers (NNS) whose native language was Mandarin. All participants began the task with subgroup conversations in their native languages, then proceeded to team meetings in English. We manipulated the exchange of subgroup conversation logs prior to team meetings: with MT-mediated exchanges versus without. Analysis of participants' subjective experience, task performance, and depth of discussions as reflected through their conversational moves jointly indicates that team meeting quality improved when there were MT-mediated exchanges of subgroup conversation logs as opposed to no exchanges. We conclude with reflections on when and how MT could be applied to enhance global teamwork across a language barrier.

The recent development of data-driven AI promises to automate medical diagnosis; however, most AI functions as 'black boxes' to physicians with limited computational knowledge. Using medical imaging as a point of departure, we conducted three iterations of design activities to formulate CheXplain — a system that enables physicians to explore and understand AI-enabled chest X-ray analysis: (i) a paired survey between referring physicians and radiologists reveals whether, when, and what kinds of explanations are needed; (ii) a low-fidelity prototype co-designed with three physicians formulates eight key features; and (iii) a high-fidelity prototype evaluated by another six physicians provides detailed summative insights on how each feature enables the exploration and understanding of AI. We summarize by discussing recommendations for future work to design and implement explainable medical AI systems that encompass four recurring themes: motivation, constraint, explanation, and justification.

Participatory sensing refers to the sensing paradigm where human participants use personal mobile devices to generate and share data from their surroundings. It holds the promise of providing information that is otherwise challenging to access, which sets the stage for understanding and resolving various social issues. However, difficulties in engaging participants often hinder the fulfillment of this promise. The current paper presents a qualitative study in the context of dockless bikesharing, where participatory sensing constitutes a backbone of the bike status monitoring system. We conducted in-depth interviews with 30 participants. These participants came from different emergent groups who took part in filing status reports for shared bikes. Our analysis indicated close associations among participants' models of engagement, their perceived (dis)connections with the sensing data, and their situated interpretation of the incentives. Based on these findings, we propose ways to engage the commons in participatory sensing for dockless bikesharing and beyond.

Workplace environments are characterized by frequent interruptions that can lead to stress. However, measures of stress due to interruptions are typically obtained through self-reports, which can be affected by memory and emotional biases. In this paper, we use a thermal imaging system to obtain objective measures of stress and investigate personality differences in contexts of high and low interruptions. Since a major source of workplace interruptions is email, we studied 63 participants while multitasking in a controlled office environment with two different email contexts: managing email in batch mode or with frequent interruptions. We discovered that people who score high in Neuroticism are significantly more stressed in batching environments than those low in Neuroticism. People who are more stressed finish emails faster. Last, using Linguistic Inquiry Word Count on the email text, we find that higher stressed people in multitasking environments use more anger in their emails. These findings help to disambiguate prior conflicting results on email batching and stress.

Multilingual teams often include subgroups of members who share a native language different from the team's common language. Linguistic choices by members of these subgroups can have implications for information exchange at the team level. We reported a field study of language use in 3 multilingual teams, each of which consisted of some native English speakers (NS) and some non-native English speakers (NNS) who shared a native language with at least one other team member. We found that NNS often shifted between English and their native language. The way language shift happened differed for formal meetings, informal conversations, and instant messaging. Language variation was often associated with shifts in content, participants, and communication medium. Further analysis indicated that language shift had both benefits and costs for team communication, depending on the context in which it happened. Based on these findings, we outline suggestions for designing multilingual collaboration systems.

When people communicate, their messages convey affect alongside informational content. The affective dimension of messages is often unclear and open to multiple interpretations especially in an intercultural context. Thus, interlocutors may or may not achieve a state of affective grounding in which each person's affective behaviors are correctly interpreted by his/her partners. The current study examines the effects of culture on affective grounding. We conducted a laboratory experiment in which pairs of participants, half from America (A) and half from China (C), collaborated over instant messaging (IM). We found that affective grounding was harder to achieve for AA and AC pairs, but easier for CC pairs. We propose several design solutions to facilitate affective grounding in remote collaborations.

Conversational grounding, or establishing mutual knowledge that messages have been understood as intended, can be difficult to achieve when some conversational participants are using a non-native language. These difficulties in grounding can be challenging for native speakers to detect. In this paper, we examine the value of signaling potential grounding problems to native speakers (NS) by displaying how non-native speakers (NNS) use automated transcripts and bilingual dictionaries. We conducted a laboratory experiment in which NS and NNS of English collaborated via audio conferencing on a map navigation task. Triads of one NS guider, one NS follower, and one NNS follower performed the task using one of three awareness displays: (a) a no awareness display that showed only the automated transcripts, (b) a general awareness display that showed whether each follower was reading the automated transcripts and/or translating a word; or (c) a detailed awareness display that showed which line of the transcripts a follower was reading and/or which words he/she was translating. NS guiders and NNS followers collaborated most successfully with the detailed awareness display, while NS guiders and NS followers performed equally across conditions. Our findings suggest several ways to improve systems to support multilingual collaboration.

Machine translation (MT) creates both opportunities and challenges for multilingual collaboration: While MT enables collaborators to communicate via their native languages, it can introduce errors that make communication difficult. In the current paper, we examine whether displaying two alternative translations for each message will improve conversational grounding and task performance. We conducted a laboratory experiment in which monolingual native English speakers collaborated with bilingual native Mandarin speakers on a map navigation task. Each dyad performed the task in one of three communication conditions: MT with single output, MT with two outputs, and English as a common language. Dyads given two translations for each message communicated more efficiently, and performed better on the task, than dyads given one translation. Our findings show the value of providing multiple translations in multilingual collaboration, and suggest design features of future MT-based collaboration tools.

Real-time transcripts generated by automated speech recognition (ASR) technologies have the potential to facilitate communication between native speakers (NS) and non-native speakers (NNS). Previous studies of ASR have focused on how transcripts aid NNS speech comprehension. In this study, we examine whether transcripts benefit multiparty real-time conversation between NS and NNS. We hypothesized that ASR transcripts would be more beneficial when the transcripts were publicly shared by all group members as opposed to when they were seen only by the NNS. To test our hypothesis, we conducted a lab experiment in which 14 groups of native and non-native speakers engaged in a story-telling task. Half of the groups received private transcripts that were available only to the NNS; the other half received publicly shared transcripts that were available to all group members. NS spoke more clearly, and both NS and NNS rated the quality of communication higher, when transcripts were publicly shared. These findings inform the design of future tools to support multilingual group communication.

Previous studies have shown that people can effectively detect emotions in text-only messages written in their native languages. But is this the same for non-native speakers' In this paper, we conduct an experiment where native English speakers (NS) and Japanese non-native English speakers (NNS) rate the emotional valence in text-only messages written by native English-speaking authors. They also annotate all emotional cues (words, symbols and emoticons) that affected their rating. Accuracy of NS and NNS ratings and annotations are calculated by comparing their average correlations with author ratings and annotations used as a gold standard. Our results conclude that NNS are significantly less accurate at detecting the emotional valence of messages, especially when the messages include highly negative words. Although NNS are as accurate as NS at detecting emotional cues, they are not able to make use of symbols (exclamation marks) and emoticons to detect the emotional valence of text-only messages.

We propose to improve real-time communication between people who do not share a common language by foregrounding potential problems in machine translation. We developed a prototype chat tool that displays two parallel translations of each chat turn, with the thought that comparing the translations might both highlight problems and provide resources for resolving them. We conducted a user study to investigate how people use and like such an interface compared to a standard one-translation interface. On balance, users preferred two translations to one, using them to both notice differences and infer meaning from uncertain translations, with no increase in workload. This suggests that this interface may help improve cross-lingual communication in practical applications and lays the groundwork for a larger design space around systems that highlight possible errors to support communication.

Traditional communication tools tend to make their presence known, e.g., "when my collaborators and I are using IM to discuss our work, how could we not realize the actual presence of IM?" In the case of machine translation (MT) mediated collaborations, however, the absence or presence of MT is not obvious. English sentences with poor grammar can result from both a partner's lack of fluency and errors in the MT process. We hypothesize that partners' attributions about the source of the errors affects their collaboration experience. To test this hypothesis, we conducted a laboratory experiment in which monolingual native English speaking participants collaborated with bilingual native-Mandarin speakers on a map navigation task. Participants were randomly assigned into a 2 (beliefs about MT: absence vs. presence) by 2 (actual mediation of MT: absence vs. presence) experiment design. Beliefs about presence of MT significantly impacted the collaboration experience, opening new opportunities for both research and design around MT-mediated collaborations.

Machine translation (MT) has the potential to allow members of multilingual organizations to interact via their own native languages, but issues with the quality of MT output have made it difficult to realize this potential. We hypothesized that highlighting keywords in MT output might make it easier for people to overlook translation errors and focus on what was intended by the message. To test this hypothesis, we conducted a laboratory experiment in which native English speakers interacted with a Mandarin-speaking confederate using machine translation. Participants performed three brainstorming tasks, under each of three conditions: no highlighting, keyword highlighting, and random highlighting. Our results indicated that people consider the identical messages clearer and less distracting when the keywords in the message are highlighted. Keyword highlighting also improved subjective impressions of the partner and the quality of the collaboration. These findings inform the design of future communication tools to support multilingual communications.

Collaboration is important to successful organizations and how coworkers are selected is crucial to the dynamics of effective collaborations. In this study we explore how people use social network information, which is increasingly accessible on enterprise systems in organizations, to choose people with whom to collaborate. We conducted a scenario-based study of 459 respondents in a global high-tech company. Our data indicate cultural differences in how social network information was valued when choosing a collaborator. The Chinese, consistent with the cultural value of Guanxi, more closely followed a closure model, whereas Americans favored neither a closure nor a structural holes model. These results provide new insights into how needs for social network information may vary between cultures and how social networking sites might support workers in choosing collaborators from within and across national cultures.

The global expansion of the use of online communities, including social networking sites, necessitates a better understanding of how people self-disclose online, particularly in different cultures. In a scenario-based study of 1,064 respondents from the United States and China, we aimed to understand how self-disclosure is affected by communication mode (face-to-face vs. online), type of relationship and national culture. Our findings show that national culture interacts with communication mode and type of relationship to affect the extent of self-disclosure. Our analysis also suggests that peoples' disclosure depends on characteristics of the relationship, e.g., closeness and openness. Our results shed new light on how online communities might be designed for users in different cultures and for intercultural collaboration.