iCity: Urban Informatics for Sustainable Metropolitan Growth

The iCity urban transport project focuses on the development of data analytics transportation and transit planning tools that could increase individual and community participation in the development, planning, and design of transportation systems interfaces.

This ongoing project is a collaboration between multiple institutions, led by the University of Toronto, and includes OCAD University, University of Waterloo, and IBM Canada. OCAD's role is the third theme of this multi-year project and focuses on developing a visualization and visual analytics tools that can interpret the vast amount of quantitative data gathered from the socio-technical and technological systems that are embedded in urban life. 

The OCAD U iCity team employed a user-centered process for design, exploring visualization techniques based on user interaction with urban transportation applications. A taxonomy was developed that considered user tasks, level of engagement, and type of data input or output. Researchers also interviewed experts from within the urban transportation sector to identify their visualization needs and challenges. This project has delivered many open source research projects including Betaville, StoryFacets, Compara, and more. The current stage of the project for OCAD University and the visualization theme works directly with the recent development of the Toronto Waterfront in partnership with Waterfront TO, ESRI, and Sidewalk Labs.

As an interactive system resource, iCity sets out the conditions for individuals and groups to highlight their needs/wants/values and to particpate in strategic planning opportunities, facilitating a more democratic and participatory urban design process.

Additional resources:
Read "Analyzing student travel patterns with augmented data visualizations"[1], available through OCAD's Open Research Repository, here.
iCity at the University of Toronto

 

 

1. Skelton, Carl and Juneja, Manpreet Kaur and Dunne, Cody and Bowes, Jeremy and Szigeti, Steve and Zheng, Minsheng and Gordon, Marcus A. and Diamond, Sara (2017) Analyzing student travel patterns with augmented data visualizations. In: Proceedings of the 2017 ACM Conference Companion Publication on Designing Interactive Systems, Edinburgh, United Kingdom, 10-14 Jun 2017. Available at http://openresearch.ocadu.ca/id/eprint/1868/

 2D map with interactive 3D infographics representing StudentMoveTO data generated using Betaville
Friday, June 15, 2018 - 10:15am
Lab Member: 
Jeremy Bowes
Marcus A. Gordon
Dr. Steve Szigeti
Dr. Sara Diamond

ViewerCentric: Visualization engineering towards a tool for media discoverability

This ongoing project sees researchers from OCAD’s Visual Analytics Lab working closely with Magnify Digital. It applies data analytics strategies and visualization best practices to the development of ViewerCentric, a visualization dashboard that allows users in the film, television, and media distribution sectors to understand complex data sets.

The data sets include streaming social media data and static data related to consumer habits. Visualization of this complex data helps content creators to better understand their audiences, increasing their discoverability.

A key component of this research is finding ways of combining multiple data sets and presenting the results in an actionable way. The ViewerCentric interface provides its users with the means to develop effective and measurable, online marketing strategies; find and assess audiences, identify opportune channels for reaching these, and evaluate messaging, funding and advertising opportunities and reports that can be submitted to funders, broadcasters, sponsors, and stakeholders.

Researchers will extend the system to other cultural content that has or could have a digital component or tag such as visual art, live entertainment, music and publishing - supporting its discoverability and user analytics. Currently editors and independent producers rely on hunches and creative vision without understanding the varied demographic differences of their audiences into account, while advertising agencies and brands primarily consider data. The objective is to help cultural industries and not-for-profits monetize content and balance personalization, market drivers and editorial direction.

 

 

We acknowledge the support of the Natural Sciences and Engineering Research Council of Canada (NSERC).
Cette recherche a été financée par le Conseil de recherches en sciences naturelles et en génie du Canada (CRSNG).

Friday, May 18, 2018 - 1:30pm
Lab Member: 
Sana Shepko
Jad Rabbaa
Afrooz Samaei
Marcus A. Gordon
Dr. Steve Szigeti
Dr. Sara Diamond

EMOTION AND SENTIMENT ANALYSIS IN TEXT

Research addressed RBC need for tools to help identify the emotional response of clients regarding bank services in order to improve their customer services. As of date, they are interested in a software solution to help them visualize networks of subsidiaries, in order to analyse money flow between different counterparts (borrowers and lenders)

 

GOALS & MISSION:
_________________________________________________________________________

To develop visualization analysis tools which can be used (internally) by RBC to better understand existing data.

 

RELATED PUBLICATIONS:
_________________________________________________________________________

Gali, G., Oliver, S., Diamond, S. & Chevalier, F. (2012). Visualizing Sentiments in Business--Customer Relations with Metaphors, in ACM Proceedings  of the SIGCHI conference Extended Abstracts on Human Factors in Computing Systems (CHI ’12), pp. 1493—1498.

Infographic
Monday, August 11, 2014 - 3:45pm
Lab Member: 
Dr. Sara Diamond
Dr. Steve Szigeti
Dr. Fanny Chevalier

ENHANCED IDENTIFICATION AND VISUALIZATION OF RELEVANT SOCIAL MEDIA

Three related factors appear to be relevant in allowing an understanding of online behaviors: attention (the time that individuals and groups expend); influence (the relationships between ideas, products and behaviors) and affect (the emotions and sentiments that are expressed in relation to ideas and products). The extraction of accurate data, then the analysis of these factors in online behavior, and the charting and representation of relationships between these factors poses a significant challenge. For one thing, these factors need to be related to specific content. Data analytics and visualization tools are needed to represent each factor and to chart these relationships. There is very little research to date that works across these fields. This large-scale project seeks to shed light on each element of online social media practice and to then draw relationships between these elements.

Research Description:
_______________________________________________________________________

People perform topic-based content exploration on large-scale social media systems. Such sites continue to expand rapidly. For example, Twitter continues to grow around the globe at a record pace. Just a year ago, they delivered 65 million Tweets a day. Today, they generate over 200 million Tweets per day. One year ago, there were approximately 150,000 registered Twitter apps. Now, there are more than one million. Facebook has more than 800 million active users of which more than 50% log on to Facebook in any given day where the average user has 130 friends. Seventy-seven percent of active Internet users read blogs. At the same time specialized media companies, brand development agencies and brands have developed social media applications that allow their users to communicate and at the same time, allow them to track the resulting data.

Editorial and business leaders see value in understanding the emotional tone, influences, attention span and diversity of their various sections and offerings, contributors and readers. Attention and influence, for example, currently directly impact advertising dollar interest in an article. In going digital, media publications have added commentary in the form of opinion blogs by its core of writers as well as ample opportunity for readers to vote and comment. Currently a majority of online media allow readers to express their thoughts and opinions on content through social media commentary. This information can impact advertising sales, decisions on style and relatedness of writers and design and even the kind of influence that different sections, authors or columns may have. Editorial leadership is eager to better manage the means for reader commentary. At the same time it is valuable to understand any underlying patterns that suggest reasons for specific emotional tone. Discovering sentiments, patterns and relationships embedded in articles as well as comments is important for tracking the newspaper’s role in shaping public opinion on contemporary issues and the ways that readers interact with these opinions. It can help media analysts better understand the impact of sentiments on news events. What is more, new tools, on multiple platforms can be developed for media users that allow them to shape their emotional content and respond to others, and chart the influence of their ideas, media patterns and behaviors.

For almost a decade contemporary brands have relied on a growing direct dialogue with their consumer base through social media, and gamification (direct play as a means of polling). These relationships engender loyalty and provide a rich source of data to understand and predict consumer behaviors. Consumer opinion that is expressed in response to new offerings, system breakdowns, or customer service is of critical importance in a world where viral trends erupt quickly with significant impact. Events and opinion outside of an immediate enterprise can have a direct impact in a social media era. Marketing and advertising companies analyze consumer attitudes and relationships to brands for trend analysis and product development. The technology of “predictive analytics” is being fine-tuned by digital media and ICT companies with new offerings such as inferSYTEMS. While the technology of monitoring is becoming more sophisticated, the underlying assumptions of analysis have not changed dramatically for many years, continuing to rely on twentieth century psychology structures. Brands and media analysis companies seek to bring together social media data with data that tracks consumer behaviors – in specific their attention to media, to products and services and their consumption patterns.

In some areas, e.g., healthcare, free-form texts are the most common form of valuable data. These data range from doctor’s notes, descriptions of patient histories, to healthcare-related messages posted by patients on social media such as blogs, bulletin boards, and discussion forums. Such narrative text data contain the most valuable information for physicians to use in their practice and for public and government agencies to make their healthcare-related decisions. Recently, the New York Times reported on a study by MIT researchers, which showed that companies included in their study that adopted data-driven decision-making achieved 5-6% higher productivity than those that did not.

Since data are continuously generated every day in large volumes, the sheer amount of data is too overwhelming for humans to read and analyze manually. Automatic text analysis tools are in great need to discover the hidden information trapped inside the free-form texts. For example, a tool that identifies and analyzes the healthcare-related posts in social media can detect public opinions, activities and preferences in healthcare-related issues.

Understanding consumer opinion of reliability and service quality across an industry like banking can have an impact on a specific company’s quality of service as well as enabling an entire industry to improve. Natural language analysis, data mining and information retrieval are key techniques that can be used to build such text analysis tools.

It is difficult to discern meaning by extracting information piece by piece. We hypothesize that taking a data-driven design approach to visualizing content would make the aggregate meanings more apparent. The advantage of working with this partially processed data is that issues of confidentiality do not arise since any confidential or client information has been abstracted from the media. A second advantage is that research can also focus on visualization and design issues rather than duplicate commercially available linguistic parsing capabilities.

Colourful lines from design piece
Colourful lines from design piece
Colourful lines from design piece
Monday, September 14, 2015 - 3:45pm
Lab Member: 
Dr. Sara Diamond

DATA AND VISUAL ANALYTICS FOR DECISION MAKING IN NEXT GENERATION

GOALS & MISSION:

This project intends to develop tools to support media companies in transition from print to digital through addressing the following research questions:

1) How do subscribers and non-subscribers consume print and/or online media – what is similar and what different?

2) How can social media data be leveraged to build and retain readers, and to inform a sophisticated next generation personalized recommendation system?  

INDUSTRY PARTNER:

The Globe & Mail

RESEARCH LEADS:

Dr Sara Diamond and Dr Steve Szigeti

RELATED PUBLICATIONS:

Diamond, S. & Szigeti, S. (2013). Social Media Data Visualization Case Study: Globe and Mail. Workshop: CIVDDD Collaborative Research in Big Data Analytics and Visualization. At CASCON 2013, November 18-20, 2013. Toronto, ON.conference Extended Abstracts on Human Factors in Computing Systems (CHI’12), pp. 1493--1498.

Oliver, S., Gali, G., Chevalier, F. & Diamond, S. (2012). Discursive Navigation  of Online  News,  in ACM  Proceedings  of the Designing Interactive Systems Conference (DIS’12), pp. 82—85.

Sponsor(s): 
Research Paper image
Monday, August 11, 2014 - 3:45pm
Lab Member: 
Dr. Sara Diamond
Dr. Fanny Chevalier
Symon Olivier

THE CARE AND COGNITION MONITOR

Visual analytic tools, combined with social networks and mobile platforms, make it possible to create multi-dimensional, holistic pictures of people’s health care and condition and expand the scope of information addressed in medical records. The Care and Condition Monitor (CCM) is a tablet-based, networked visual analytics tool for collecting, structuring and analyzing informal and qualitative healthcare data and visualizing it in a circular format. It illustrates how social communication within teams of caregivers enables capturing of longitudinal informal data that can (a) result in rich and meaningful information visualizations, (b) improve comprehension of healthcare data and changes in condition over time, and (c) support medical decision making. 

Keywords: 
Screenshot of visual analytics tools
Monday, September 14, 2015 - 3:45pm
Lab Member: 
Hudson Pridham
Dr. Steve Szigeti
Dr. Sara Diamond
Dr. Bhuvaneswari Arunachalan

THE STACKED STACKED BAR GRAPH

Stacked-stacked bar graph is the working title of a visualization that builds on the strengths of a stacked bar graph. Where a stacked bar graph allows for a visual comparison of the parts to the whole, our proposed visualization further divides the parts to allow for additional points of comparison.

For more information, see:
Szigeti, S., Patrasc, J., Schnitman, D., and Diamond, S. 2014. “The Stacked-Stacked Bar Graph: A New Twist on an Old Visualization.” IEEE InfoVis Proceedings.

Stacked-stacked bar graph is the working title of a visualization that builds on the strengths of a stacked bar graph.
Stacked-stacked bar graph is the working title of a visualization that builds on the strengths of a stacked bar graph.
Monday, September 14, 2015 - 3:45pm
Lab Member: 
Dr. Sara Diamond
Dr. Steve Szigeti
Joana Patrasc
David Schnitman

THE INFINITE CANVAS

The Infinite Canvas is a tablet display for news search results display that takes advantage of spatial relationships to understand connections between articles.  The articles are sorted by relevance along the vertical direction, and by date along the x direction.

For more information, see: 
Szigeti, S. Schnitman, D., Peters, J., Vu, P. & Diamond, S. (2015). Infinite Canvas: A novel presentation of newspaper search results on a tablet. MobileHCI 2015, August 24-27, Copenhagen, Denmark.

Screenshot from the Infinite Canvas - a tablet display for news search results
Screenshot from the Infinite Canvas - a tablet display for news search results
Monday, September 14, 2015 - 3:45pm
Lab Member: 
Dr. Steve Szigeti
David Schnitman
Jessica Peter
Dr. Sara Diamond

A TANGIBLE USER INTERFACE FOR DATA QUERY

We are creating a Tangible User Interface (TUI) designed to interactively query a database.  While much work has been done on TUI, showing that they encourage collaboration and positively enhance user experience, few tangible systems have been designed specifically for data analysis tasks.  Our system combines a tabletop (non-digital) graspable user interface with a two-dimensional screen display; the user interrogates the data by placing tokens on or off the tabletop and the screen displays the results of the user’s query.  The objects are tagged using fiducial markers, which are identified with open-source ReacTIVision computer vision software, and the visualization code is written in Processing.  We use radio station listenership demographic data for our current prototype, but the system can be used to query any type of database.

Below is a schematic of our tangible data query system.  Users create queries by placing objects onto a table, which has a camera placed discretely below it; the results of the query are displayed onto an overhead screen placed at one end of the table.  A video of the interaction can be viewed here: https://www.youtube.com/watch?v=XfTvTsqG5ZI

 

Publications:

Jofre, A., Szigeti, S., Tiefenbach-Keller, S., Dong, L.-X., Diamond, S. “Manipulating Tabletop Objects to Interactively Query a Database” (2016) CHI’16 Extended Abstracts (Chi 2016 San Jose May 7-12) 

Jofre, A., Szigeti, S., Diamond, S. "Citizen engagement through tangible data representation" Foro de Educación (January-June 2016) vol. 14, n. 20 

Jofre, A. Szigeti, S., Tiefenbach-Keller, S., Dong, L.-X., Tomé, F., Czarnowski, D., Diamond, S. (2015) "A Tangible User Interface for Interactive Data Visualization" Proceedings of the 2015 Conference of the Center for Advanced Studies on Collaborative Research. IBM Corp., CASCON2015, November 2-4, 2015, Toronto, Ontario.

Szigeti, S., Stevens, A., Tu, R., Jofre, A., Gebhardt, A., Chevalier, F., Lee, J. & Diamond, S. (2014) Output to Input: Concepts for Physical Data Representations and Tactile User Interfaces. Proceedings of CHI14 Works‐in‐Progress (Toronto, ON).

Tangible user interface
Diagram showing 3 people using the table-based tangible user interaface
Tuesday, September 8, 2015 - 3:45pm
Lab Member: 
Dr. Ana Jofre
Dr. Steve Szigeti
Dr. Sara Diamond
Frederico Tomé
Dr. Fanny Chevalier
Embed Video: