Érudit and Vialab Collaboration Projects

Covid Connect: Chat-Driven Anonymous Story-Sharing for Peer Support

Interaction-Driven Metrics and Bias-Mitigating Suggestions

A Case Study of Visual Explanation by Generative Machine Learning

A unique explainable AI (XAI) system and interface, and a user study pitting it against a more traditional "black box" AI model in order to study the benefits and effects of our XAI system on human-AI trust and synchronization.

A Comparative Study of Visualization Task Performance and Spatial Ability

An investigation into how people's cognitive traits correlate to their profession, and how these factors influence their performance on data analysis tasks; paving the way for discussion about how data visualization can cater to different professions.

Card-IT Language Learning

A novel approach to training and testing Italian verb morphology by developing a flashcard application with a finite-state morphological (FSM) analyzer which both analyzes a user’s input and dynamically generates specific verb forms (flashcards).

Visual Analytics Tools for Academic Advising

Predicting the likelihood of a student withdrawing from the university after their upcoming semester with machine learning.

Academia is Tied in Knots

A data visualization project aimed at giving visibility to the issue of sexual harassment in the academic community.

Tilt-Responsive Techniques for Digital Drawing Boards

An investigation into a range of app-specific transitions on tilt-adjustable drawing boards in response to changes in display angle such as reading vs. writing (annotation), public vs. personal, and shared person-space vs. task-space, among others.

Textension: Digitally Augmenting Document Spaces in Analog Texts

A framework that allows people who work with analog texts to leverage the affordances of digital technology, such as data visualization, computational linguistics, and search, using any web-based mobile device with a camera.

Eye Tracking for Target Acquisition in Sparse Visualizations

A novel marker-free method for identifying screens of interest when using head-mounted eye-tracking for visualization in cluttered and multi-screen environments.

Guidance in the human–machine analytics process

An in-depth investigation into the efficacy of and potential use-cases for guiding users through visual analytics tasks using software systems, as well as the general automation of data analysis tasks.

Hierarchical Matrix for Visual Analysis of Cross-Linguistic Features

A visualization technique for cross-linguistic error analysis in large learner corpora that combines a matrix with a tree diagram to create custom investigative views.

A Visual Analytics Framework for Adversarial Text Generation

A framework that enables a user to more easily make corrections to adversarial texts by extending existing attack algorithms to facilitate human intervention.

A Transdisciplinary Approach to Problem-Driven Visualizations

A new methodological paradigm that provides an alternative perspective on problem-driven visualization work.

Guided Topic Model Refinement using Word-Embedding Projections

A framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic.

Discriminability Tests for Visualization Effectiveness and Scalability

Exploring the use of an image similarity measure, the Multi-Scale Structural Similarity Index (MS-SSIM), for testing the discriminability of a data visualization across a variety of datasets.

Saliency Deficit and Motion Outlier Detection in Animated Scatterplots

A crowdsourced experiment measuring the accuracy of motion outlier detection in multivariate, animated scatterplots.

ActiveInk: (Th)Inking with Data

A system enabling people to seamlessly transition between exploring data and externalizing their thoughts using pen and touch.

Visual Analytics for Topic Model Optimization

An explainable, mixed-initiative topic modeling framework that integrates speculative execution into the algorithmic decision-making process.

ThreadReconstructor: Modeling Reply-Chains to Untangle Conversational Text

A visual analytics approach for detecting and analyzing the implicit conversational structure of discussions, especially in political debates and forums.

Detecting Negative Emotion for Mixed Initiative Visual Analytics

Generating efficient models for detecting negative mind states using training data collected from multiple sensors including GSR and eye-tracking.

EduApps: Helping Non-Native English Speakers with Language Structure

A project that aims to analyze errors made when learning a second language by learners from specific language backgrounds using learner corpora

Metatation: Annotation for Interaction to Bridge Close and Distant Reading

A study and subsequent tool design focused on leveraging a critic’s annotations as implicit interactions for initiating context-specific computational support that automatically searches external resources.

DataTours: A Data Narratives Framework

A descriptive hierarchical framework to formalize and guide the design of automated tours for data exploration and discuss challenges evoked by the framework in the automated authoring of such tours.

Perceptual Biases in Font Size as a Data Encoding

A collection of empirical studies showing that factors that are irrelevant to encoded values can influence comparative judgements of font-size, and strategies to mitigate perceptual biases of font-size.

Progressive Learning of Topic Modeling Parameters

A modular visual analytics framework, tackling the understandability and adaptability of topic models through a user-driven reinforcement learning process.

Abbreviating Text Labels on Demand

A new technique to automatically make words as short as they need to be to maintain text legibility and readability.

NEREx: Named-Entity Relationship Exploration in Conversations

An interactive visual analytics approach for the exploratory analysis of verbatim conversational transcripts.

ConToVi: Multi-Party Conversation Exploration using Topic-Space Views

A novel visual analytics approach to analyze speaker behaviour patterns in multi-party conversations.

PhysioEx: Visual Analysis of Physiological Event Streams

A  visual dashboard for multiple heterogeneous data streams using a novel visualization technique that visually integrates data values over time to reveal the frequency, duration, and timing of significant features in streaming data.

Using Visual Analytics of Heart Rate Variation to Aid in Diagnostics

An interactive visualization tool for exploring RR interval data (the time between consecutive heart beats) to support diagnostics.

Off-Screen Desktop

A collection of spatial navigation techniques that make use of the space around the display to extend direct manipulation beyond the desktop screen.

PivotSlice

An interactive visualization technique that provides efficient faceted browsing as well as flexible capabilities to discover data relationships.

Reading Comprehension on Mobile Devices

A touch-based reading interface for tablets designed to support vocabulary acquisition, text comprehension, and reduction of reading anxiety.

#FluxFlow

An interactive visual analysis system for revealing and analyzing anomalous information spreading in social media.

Balancing Clutter and Information in Large Hierarchical Visualizations

A new approach for adjusting the level of abstraction of hierarchical visualizations as a function of display size and dataset.

Glidgets

A new combined direct manipulation and visualization technique for exploring and querying dynamic graphs.

DimpVis Direct Manipulation for Visualization

A new direct manipulation technique for interacting with visual items in information visualizations to enable exploration of the time dimension.

Lexichrome: Lexical Discovery with Word-Color Associations

A web application that explores the popular perception of relationships between English words and eleven basic colour terms using interactive visualization.

SentimentState: Exploring Sentiment Analysis on Twitter

A web-based visualization tool called SentimentState that performs sentiment analysis on tweets from a user’s Twitter account.

DAViewer: Facilitating Discourse Analysis with Interactive Visualization

An interactive visualization system for assisting computational linguistics researchers to explore, compare, evaluate and annotate the results of discourse parsers.

TandemTable

A multi-touch tabletop system designed to break down communication barriers between partners with a special focus on supporting those who are learning languages.

Investigating the Semantic Patterns of Passwords

Simple Multi-Touch Toolkit

A simplified software framework built around the Processing language.

Exploring Text Entities with Descriptive Non-photorealistic Rendering

A novel approach to text visualization which integrates 3D non-photorealistic rendering with information visualization.

Bubble Sets

A visualization technique for data that has both a primary data relation with a semantically significant spatial organization and a significant set membership relation in which members of the same set are not necessarily adjacent in the primary layout.

Parallel Tag Clouds

A new way to visualize differences amongst facets of very large metadata-rich text corpora that combines graphical elements from parallel coordinates and traditional tag clouds.

VisLink: Revealing Relationships Amongst Visualizations

A method by which visualizations and the relationships between them can be interactively explored.

DocuBurst: Visualizing Document Content using Language Structure

The first visualization of document content that takes advantage of the human-created structure in lexical databases.

Tabletop Text Entry Techniques

An examination of text-entry methods for tabletop displays.

Lattice Uncertainty Visualization: Understanding Machine Translation

A novel visualization intended to reveal the uncertainty and variability inherent in statistically-derived outputs of language technologies.

WordNet Visualization

A design paradigm to generate visualizations which maximize the usability and utility of WordNet.