KIXLAB's research is made possible by generous financial support from KAIST, the National Research Foundation of Korea (NRF), the Institute for Information and Communications Technology Promotion (IITP), LG Electronics, and Samsung Electronics.
Crowdsourcing Techniques for Annotating Context, Emotion, and Intention on Dialog Videos
Dialog videos contain rich contextual, emotional, and intentional cues of the characters and their surroundings. In this project, we aim to build a crowdsourcing platform that collects these information from a large dialog video dataset. The collection and aggregation process can be challenging because the temporal dimension of the dataset has to be considered, and the labels are multi-dimensional and can be highly subjective. We combat these challenges by exploring crowdsourcing techniques to design workflows and answer aggregation methods that efficiently collects multi-dimensional labels and overcome the subjective nature of the collected annotations.
Enhancing Informal Communication in the Workplace with Online and Physical Data
Informal communication is a kind of communication that is not scheduled in advance, unlike recurring meetings. Informal communication is known to increase collaboration and information sharing in the workplace. To promote informal communication with technology, previous approaches have captured and displayed the user’s availability information, like in a messenger app that shows the user’s current status. In this project, we take the position that it is crucial to not only consider the user’s immediate status but also their long-term usage patterns and even personality. To infer the user’s availability for informal communication, we analyze both online data (messenger logs) and physical data (sound sensors, beacons, etc.).
This research is sponsored by IITP (Ministry of Science and ICT) under “Development of Autonomous IoT Collaboration Framework for Space Intelligence” project.
RecipeScape: Mining and Analyzing Diverse Processes in Cooking Recipes
In this research, we explore how analyzing cooking recipes in aggregate and in scale helps discovering the core values in the collective cooking culture, and answer fundamental questions like ‘‘what makes a chocolate chip cookie a chocolate chip cookie’’. Aspiring cooks, professional chefs and cooking hobbyists share their recipes online resulting in thousands of different procedural instructions towards a shared goal. We introduce RecipeScape, a prototype interface which supports visually querying, browsing and comparing cooking recipes at scale. We also present the underlying computational pipeline of RecipeScape that scrapes recipes online, extracts their structural semantics from ingredient and instruction information, constructs a procedural graphical representation, and computes similarity between pairs of recipes.
Joint research project with Stanford University
Exprgram: Language Learning Interface for Development of Pragmatic Competence through Learnersourcing Video Annotation
The real world conversations are diverse in expressions depending on the context such as the relationship between speakers, location or time. While there are multiple ways to greet, apologize, compliment others, language learning materials often fail to provide enough diverse situations and rather put more focus on the meaning of words, reading or listening comprehension and grammar. This research combats the challenge by exploring large scale natural conversations through video mining. Unlike unauthentic dialogues from existing materials, videos in the target language can expose learners to authentic and diverse language situations. We introduce Exprgram, a learnersourced, web-based interface for teaching diverse language expressions.
Interaction Techniques for Intelligent Agents Powered by Large-Scale Conversation Mining
Even though recent improvement in speech recognition and NLP accelerated development in conversational agents, keeping user needs and usability in mind and setting the right expectation and mental model is crucial in improving interaction between agents and humans. We try to apply HCI approach to conversational agents and build right interaction model for conversational agents, which is proactive, natural and flexible. For those purposes, we are mining contexts from conversations and implementing strategies for conversational flow and user-agent collaboration.
Micro-NGO: An Online Social Activism Platform with a Mediator Bot
Real world problems are a popular theme of online discussions. While people can gather useful insights from diverse perspectives during the discussion, it is rare to observe deliberation of collective actions. Micro-NGO is a bot-mediated social discussion platform that fascilitates deliberation of self-organized collective action. The bot helps a group by assisting in task disambiguation and domain specific knowledge scaffolding.
Collaborative Dynamic Query
The goal of this project is to reduce the communication cost of small group decision making. When people make decisions on questions such as where to travel or what to eat with other people, a lot of conversation is required to make decisions reflect as many opinions as possible. As a solution, we suggest an interface called Collaborative Dynamic Query. It helps people represent their preferences for several criteria and shows the preferences of other group members. Also, preferences of a group can be used for recommendation for available items.
Rally(아, 쫌!): A Data-driven Community Petition Platform
Often complaints and request from community members’ happen in an ad-hoc manner, in turn, it couldn’t draw the attention from the decision maker. We propose a crowdsourced petition platform Rally to empower the community members’ voice with unified communication pipeline to the decision maker. We focus on the petition which is one of the most common protocols between community members’ and decision makers.
Improving Government Transparency with Social Computing
How can we build an interactive platform for citizens to learn, discuss, and take collective action on important social issues? The ambitious aim of this project is to design and experiment with a system that helps to increase transparency and public trust. We achieve this by employing social computing techniques and creating a new public monitoring and feedback channel. Citizens join our platform to learn and be empowered by participation, by giving their opinion about political issues and performing micro-tasks such as tagging, adding related information, and requesting missing information. The issues originate from current congressmen’s campaign promises.
Through a series of interviews, surveys, prototypes, and live deployments, we want to deepen our understanding of communities, citizensourcing, civic participation, personalization, and other related topics.
Fall 2017 Undergraduate Theses
Constructing Political Personas that Reflect Voters’ Interests
in Election Promises
Ina Ryu: A Qualitative Analysis of Conversational Techniques in Chatbots
Hyeong Cheol Moon: A Comparison of Korean Sentence Classification Models for Chatbots
Summer 2017 Internship Projects
Learnersourcing Subgoal Labels for Student Solutions
Amy Han: Designing Interactive Distance Cartograms to Support Urban Travelers
Wookjae Byun: User Meets Chatbot for the First Time
Léonore Guillain: RecipeScape: Mining and Analyzing Diverse Processes in Cooking Recipes
Suhwan Jee: Asynchronous-Interactive Feedback Interfaces
Jooyoung Lee: Designing User Interfaces for Supporting Collaborative Decision-Making
Beomsu Kim: Summarizing Image Clusters with Generative Adversarial Nets
Kyungje Jo: Learning Diverse Language Expressions through Video-mining
Hyunwoo Kim: Improving Government Transparency with Social Computing
Jonghyuk Jung: Visualizing Objects and Their Relationships in Living Spaces with Social Media Images
Winter 2017 Intern Projects
Learning Diverse Language Expressions through Video-mining
Jaesung Huh: Assisting essay writing through showing counter-arguments
Deokseong Kim: Constructing personas by using clusters of Instagram user activities
2016 Summer Intern Projects
Improving contents of lecture video by leveraging students’ questions
Hyeungshik Jung: Annotation interface for watching learning video in mobile devices
Dongkwan Kim: Identifying contributing factors of pairwise affinity between politicians
Jiwoo Park: Online Interface that Promotes Higher Level Questions
Taekyung Park: The Effect of Emphasizing Community and Individual Value in Learners’ Engagement in Activities