Title: How Can Data Science Make the World a Better Place – Some Examples and Personal Thoughts.
Abstract: We will present briefly several projects that - working with various types of data - had very different social improvement goals as their objectives. In the first project, joint work with NGOs PeaceGeeks and UMATI, we analyzed twitter traffic in Kenya. Based on Susan Benesch’s hate speech theory, the goal was to detect violence-inducing social media posts. In the second project we have analyzed the equality-driven social media activism of women in Saudi Arabia. In another project, starting with a gender studies framework describing different kinds of sexist language, we used Machine Learning and text mining to find sexism in social media (twitter) data. We will also discuss select cases of environmental and economic Data Science for the Social Good (DSSG). One elegant example involves the work of Trygg Mat Tracking, a Norwegian company that uses a specialized ocean big data to monitor, and effectively fight, illegal fishing in East Africa. The Data for Development (D4D) Data Challenge is another example of an interesting initiative in DSSG. We will close with some personal thoughts and recommendations as to what makes a good DSSG project.
Bio: Stan Matwin is the Professor and Canada Research Chair (Tier 1), and the Director of the Institute for Big Data Analytics at Dalhousie University, Canada. Internationally recognized for his work in Machine Learning and Artificial Intelligence, he has authored and co-authored more than 300 refereed papers, supervised more than 70 graduate students, and taught Data Science on four continents. He is the Coordinator for the Applications Area of the Springer Encyclopedia of Machine Learning, and one of the founders of Ocean Data Science Inc., a new Canadian start-up. He is a Fellow of the European Coordinating Committee for AI, a Fellow of the Canadian AI Society (CAIAC), and a recipient of the CAIAC Lifetime Achievement Award.
(Slides)
Title: The pulse of a city - a glimpse at a locality using microblogs and machine learning
Abstract: Since the advent of Web 2.0 and social media, anyone with an Internet connection can create content online. Popular social media applications, such as microblogging with Twitter, are used for a number of reasons. Users can share millions of posts daily on Twitter to cover events real-time, express opinions or simply describe their daily life. Many argue that the majority of information shared this way is worthless. However, someone’s trash is someone-else’s treasure.
In this ongoing work, we present the Grebe social data aggregation framework for extracting geo-fenced Twitter data for analysis of user engagement in health and wellness topics. Grebe also provides various visualization tools for analyzing temporal and geographical health trends. A large dataset of geo-fenced twitter posts was collected to analyze three types of contexts: geographical context via prediction of user location using supervised learning, topical context via determining health-related tweets using various learning approaches and a six dimensional wellness model, and affective context via sentiment analysis of tweets using rule-based methods.
When location is determined, the information in tweets can be used, not only to learn about what is happening in a city, but also to understand users' emotions (e.g., love, fear) and sentiments (e.g., positive, negative) on topics and events as they unfold over time. An interactive visualization tool was developed to compare and contrast sentiments and emotions during different temporal periods at city level.
Bio: Osmar R. Zaïane is a Professor in Computing Science at the University of Alberta, Canada, and Scientific Director of the Alberta Machine Intelligence Institute (Amii). Dr. Zaiane obtained his Ph.D. from Simon Fraser University, Canada, in 1999. He has published more than 300 papers in refereed international conferences and journals. He is Associate Editor of many International Journals on data mining and data analytics and served as program chair and general chair for scores of international conferences in the field of knowledge discovery and data mining. Dr. Zaiane received numerous awards including the 2010 ACM SIGKDD Service Award from the ACM Special Interest Group on Data Mining, which runs the world’s premier data science, big data, and data mining association and conference.