Demos

Chatbot Evaluation Platform

Questionnaire to evaluate the performance of four different chatbots.

Chatbot

We present a chatbot that generates responses to people’s queries. The model is trained using 35,429 pair of conversations from the Big Bang Theory.

Run this demo.

Visualization tool for tweets related to food and mood

We present a tool that enables users to browse hundreds of tweets related to both food and mood. By placing these tweets on a wheel, the user can visualize how moods are correlated with a certain food.

Run this demo.

Visualization of food and mood

We present a tool that allows people to interactively review their food journeys, and to explore the interesting correlations between their nutrition intake and emotions.

Run this demo.

Visualization tool for activities of daily living

We present a tool to visualise physical exercise patterns of 48 people, who wore accelerometers that measured steps and calorie expenditure.

Run this demo, More about this project.

Emotions in Tweets about the Olympics

Temporal visualization of the emotions captured in the tweets about Olympic Games.

Run this demo, More about this project.

interactive FishEye-View Interface

We developed an interactive products recommender system based on a force-directed layout and fish-eye view. This system provides a search tool and a critiquing interface to query items intuitively. The link below gives you access to the desktop demo but there is also a mobile version of this recommender system.

Run this demo, More about this project.

Group Fun

We have developed a music group recommender system named GroupFun, which is a Facebook application that recommends music for groups of users for events, such as a graduation party.
The functions of GroupFun mainly include: 1) group management, 2) music recommendation.
Users are able to create a group, invite their friends to group, and join other groups. We are evaluating recommendation algorithms and user interfaces on this application.

Run this demo, More about this project.

Survey on Hybrid Critiquing

Given their respective strengths, a Hybrid of Example-Critiquing (EC) and Dynamic-Critiquing (DC) was developed to combine them together on the same screen, so that users can not only specify their own critiques if necessary with EC, but also obtain the knowledge of remaining recommendation opportunities and pick the suggested critiques by DC if one of them matches their desires.

Go to the survey, More about this project,
Try Example-Critiquing, Try Dynamic-Critiquing.

Online Product Finder

The system has been developed to assist users in searching for high-involvement products, such as digital cameras, tablet PCs, and laptops. It is composed of two main decision components: preference-based organization interface and example-critiquing support.
The former acts as explanation facility to help users understand the computational reasoning of recommendation generation but also critiques suggestions to guide users to make informed tradeoff navigations. The user is further supported to freely refine her/his preferences with the latter, by which s/he could choose a product to be critiqued and determine how to critique it, such as improving some of its feature on behalf of less important attributes. It gives users high level of control over the process of preference revision and feedback provision.
Run this demo, More about this project.