Interview about Ling Chatbot App, winner of the A' Mobile Technologies, Applications and Software Design Award 2023
Ling is an educational chatbot mobile application that provides reliable learning resources about equity, diversity, and inclusion to help Chinese international students to learn and prevent discrimination and harassment. The app also connects users to their school’s trustful case report sources. Through humanized conversational interaction, the app makes people talk about difficult topics easier.
View detailed images, specifications, and award details on A' Design Award & Competition website.
View Design DetailsThe inspiration for Ling really came from observing the unique challenges that many Asian international students, particularly Chinese students, face when studying abroad. During the pandemic, I saw a troubling rise in racially motivated aggression against Asian communities. In particular, international students—already adapting to new academic and social environments—were especially vulnerable. Many students I spoke with felt isolated, unsure of how to respond to incidents of discrimination or subtle biases, and sometimes were even unaware that what they were experiencing was a form of harassment.
I did it intentional. We’re dealing with sensitive and deeply personal topics, so the interaction needed to feel as human and empathetic as possible. A chatbot format lets users feel like they’re having a private, supportive conversation rather than completing a sterile questionnaire or navigating through a typical app.
I kept the information architecture very streamlined. Instead of overwhelming users with long lists of articles or resources, we embedded bite-sized educational content directly into the chat experience. When users bring up a question or concern, Ling responds in a way that’s both informative and conversational
Through these interviews, I uncovered a consistent pattern: students often weren’t sure if what they were experiencing counted as discrimination, or they felt uncertain about how to react. This ambiguity led many of them to dismiss or internalize their experiences, often at the expense of their well-being. These findings directly influenced Ling's core features.One of the main features that emerged was Ling’s ability to help users identify different types of discrimination in real-time. By talking to Ling about their experiences, students can describe situations and receive feedback on whether what they encountered could be classified as a form of discrimination. This feature was inspired by students who expressed a need for clarity and validation.Another significant feature is the direct connection to their school’s resources, like equity, diversity, and inclusion (EDI) departments. Many students I spoke with didn’t know how to seek help within their institutions or feared that their concerns wouldn’t be taken seriously. By integrating a direct link to trusted resources, Ling helps them take immediate action, whether it’s reporting an incident or accessing support services, without having to navigate complex administrative structures on their own.
Every university has a different system for handling discrimination reports, so we had to work closely with each institution to understand their protocols and technical limitations.
Each city has its own mix of cultures and challenges when it comes to discrimination, and being exposed to different perspectives helped us better understand the range of experiences international students might have.
The solution was to design a step-by-step approach that felt more like a guided conversation than an assessment. This approach allowed us to simplify complex concepts without compromising depth or empathy.First, we broke down the identification process into digestible, relatable prompts, guiding students through their experiences gradually. Ling uses simple, non-technical language to ask questions like, “Did you feel uncomfortable with something someone said or did?” instead of directly probing for discrimination indicators. This lets users reflect without feeling pressured to label their experience immediately.Next, we used conditional branching in the dialogue, where Ling’s responses change based on the user’s input. This made interactions feel personalized, so Ling could offer tailored support, such as a follow-up question to help users articulate what they’re feeling. This dynamic helps Ling feel genuinely engaged, offering empathy while leading users gently toward recognition of what they might be experiencing.
One example is when users describe an interaction where they felt uncomfortable but aren’t sure why. Ling might respond by asking, “Did someone make a comment about where you’re from or how you speak?” and then explain how assumptions or remarks based on stereotypes can be microaggressions. For instance, if a student describes being complimented for speaking “good English,” Ling explains that while it may seem positive, it can imply an expectation of inadequacy based on their ethnicity—a common type of microaggression. This helps users pinpoint the subtle nature of such comments and understand the underlying bias.
One feature I'm exploring is a peer support network, where students can anonymously share their experiences or advice with each other through Ling, moderated to ensure safety and privacy.
I regularly collect anonymous surveys and conduct follow-up interviews with volunteer users to gauge how helpful Ling has been in real-life situations.
Dive into a world of design excellence with our curated highlights. Each feature showcases outstanding creativity, innovation, and impact from the design world. Discover inspiration and learn more about these incredible achievements.
