Machine translation is often not enough for people to engage across languages due to translation errors and lack of cultural background. In addressing these challenges, my dissertation explores how AI-augmented analytics can improve computer-mediated communication between speakers of different native languages. First, to support better sense making of foreign language posts in social media, I designed SenseTrans, a tool that adds contextual information using AI-analytics such as sentiment analysis. In my future work, I intend to explore 1) how people perceive, interpret and make use of AI-generated information, and 2) how AI-augmented analytics could be applied to other settings.

Although many social media sites now provide machine translation (MT) for foreign language posts, translation of a post may not suffice to support understanding of, and engagement with, that post. We present SenseTrans, a tool that provides emotional and contextual annotations generated by natural language analysis in addition to machine translation. We evaluated SenseTrans in a laboratory experiment in which native English speakers browsed five Facebook profiles in foreign languages. One group used the SenseTrans interface while the other group used MT alone. Participants using SenseTrans reported significantly greater understanding of the posts, and greater willingness to engage with the posts. However, no additional cognitive load was associated with using an interface that provided more information. These results provide promising support for the idea of using computational tools to annotate communication to support multilingual sense making and interaction on social media.

We explore how language affects people’s attention to and engagement with social media posts in an eye-tracking experiment in which participants viewed a mock newsfeed containing English and foreign language posts, half with and half without images. Participants spent less time looking at foreign language posts than English posts, and more time looking at posts with images than those without images. Participants reported being more likely to like or comment on posts in English and posts with images. We suggest some new design ideas for supporting people’s interaction on multilingual social media sites.

Many people’s social media feeds include posts in languages they do not understand. While previous research has examined bilingual social media users’ language choices, little research has focused on how people make sense of foreign language posts. In the present study, we interviewed 23 undergraduate social media users about how they consume and make sense of posts in other languages. Interviewees reported that they often did not pay attention to or engage with foreign language posts, due to a lack of relevance and contextual knowledge. When they did actively engage with foreign language posts, interviewees did not rely solely on machine translation output but instead actively collected and combined various cues from within and outside the post in order to understand what it was about. Interviewees further reported different types of goals for trying to make sense of foreign language posts; some focused on simply extracting and understanding the emotional components of a post while others tried to gain a fuller understanding of a post, including its contextual and cultural meanings. Based on these findings, we suggest design possibilities that could better aid multilingual communication in social media.

Previous research has shown that communication technologies may make it challenging for working professionals to manage the boundaries between their work life and home life. For college students, however, there is a less clear definition of what constitutes work and what constitutes home life. As a result, students may use different boundary management strategies than working professionals. To explore this issue, we interviewed 29 undergraduates about how they managed boundaries between different areas of their life. Interviewees reported maintaining flexible and permeable boundaries that are not bounded physically or temporally. They used both technological and non-technological strategies to manage different life spheres. Interviewees saw technology as a major source of boundary violations but also as a boundary managing strategy that allowed them to achieve better life balance. Based on these findings, we propose design implications for tools to better support the boundary management processes of undergraduate students.

Selfies are everywhere on social media. Research has focused only on who is posting selfies and has not addressed the audience members viewing selfies. This study aims to fill this gap by analyzing the judgments people make of selfies posted on Facebook. Using an online experiment, we test how including a selfie on a Facebook status update changes people’s appraisals of narcissism, message appropriateness, and social attraction. We also consider how the valence and intimacy of the status update text interplay with the selfie to change social judgments. Participants rated posts with selfies as more narcissistic and inappropriate, and less socially attractive. Selfie evaluations also depended upon the valence and intimacy of the status update text. Gender of the selfie poster did not influence evaluation of posts. One implication from these results is that posting selfies on social media may lead to negative judgments about the poster.

The widespread use of mobile devices has transformed casual places into meeting places. However, in these places, it is uncommon to have shared information workspace such as a beam projector, making it inconvenient and inefficient to exchange information and to get a direct feedback. To address this challenge, we present Ubi-jector, a mobile system that provides a shared information space that is equally distributed to each participant’s mobile device and allows group members to share documents and collaborate real-time. We first characterized the information sharing patterns and identified the limitations of the current practice in meeting places without a shared workspace, by conducting qualitative user studies. Next, we implemented Ubi-jector with the design guidelines drawn in the prior stage. Also, we performed an evaluation study that showed the possibilities of Ubi-jector to facilitate an effective information sharing and foster an active participation even in poorly-equipped environments.

This research explores the uses of communication channels that couples adopt in varied geographical distance settings. We also characterize their conflict patterns and strategies for resolving the conflicts. We found that the distances between couples have a strong influence on their communication patterns. The distance is associated with typical conflicts pattern that couples confronted as well as the relationship maintenance strategies. In this research, we classify distance settings into four categories. Then, we perform semi-structured interviews with 20 couples in various distance settings. The analysis allows us to develop design guidelines for mitigating conflicts associated with the four distance categories.