Mining association and correlation of emerging keywords in tweets and social media, and how they change over time and locations
Time and location sensitive prediction models on number of cases, ICU rate, and fatality
Topic evolution in COVID-19 publications
Reference lineage of COVID-19 research
Genetic evolution of COVID-19
Information and misinformation in COVID-19 tweets
Spreading of COVID-19 scientific publications in social media, like tweets
Does inequality play any role in the degree of COVID-19 outbreak?
Dataprep: a data preparation tool and tutorial
An intense reading list will be provided. Students are expected to read extensively. The articles are available from either the web or from SFU library. A title carrying a course number is required for the specific course only and is optional for the other course.
[A survey] Artificial Intelligence against COVID-19: An Early Review by Wim Naudé
[What AI can and cannot do] Artificial Intelligence Won't Save Us From Coronavirus WIRED
[WeChat is a phenomenal social media. You should look at it.] WeChat Revenue and Usage Statistics (2020) (CMPT 456)
[What is data science?] What Data Scientists Really Do, According to 35 Data Scientists The Harvard Business Review (CMPT 459)
[A story about truth finding in web search] Google and the Cost of ‘Data Voids’ During a Pandemic WIRED
[How mobile interaction networks can help combating COVID-19] Google and Apple Reveal How Covid-19 Alert Apps Might Look WIRED
[Visualization] Visualizations That Really Work The Harvard Business Review
[A case study about crawling and knowledge graph construction. CMPT 456 uses this case in Assignment 1] The Year the Internet Thought I Was MacKenzie Bezos WIRED
[How web search and social networks may change the landscape of news business.] Big Tech Has Crushed the News Business. That’s About to Change New York Times
[Disposable contact information indeed is another kind of disguised missing data] How to Avoid Spam—Using Disposable Contact Information WIRED
[You may wonder what a sophisticated picture may look like when big data, search, advertisements, business all come together. Here is a one side story about Google] Here’s What an Antitrust Case Against Google Might Look Like WIRED
[When we present data, it is important to consider and understand the possible bias and misunderstanding for audience] Air Travel Surges by 123%! (Beware of Misleading Data Like That.) New York Times
[Let us get a quick review on medical literature mining] Recent advances in biomedical literature mining Briefings in Bioinformatics
[A social network app is not only about techniques and data, instead, it is about how to connect the right people, in the right way, at the right time] The Hot New Thing in Clubby Silicon Valley? An App Called Clubhouse New York Times
[How can AI and data management can help Microsoft buid future software? Let us watch this nice talk.] AI-Powered Data Management and the Future of Software Johannes Gehrke (Microsoft)
[What are the next challenges and opportunities in cloud computing? This is an inspiring video] A Data-Centric Lens on Cloud Programming and Serverless Computing Joe Hellerstein (UC Berkeley)
[Professor Vipin Kumar explains data science in climate and earth sciences.] Big Data in Climate and Earth Sciences: Challenges and Opportunities for Data Science Vipin Kumar (Univ. Minnesota)
[NSA built Mainway using telephone call data. You will find many concepts and ideas discussed in this course are indeeded used in Mainway. Using this case, we can also take a look at the borders among technologies, laws, and humannities.] Inside the NSA’s Secret Tool for Mapping Your Social Network WIRED
[Some hints about how Google builds and manages its internal data lake.] Goods: Organizing google's datasets SIGMOD 2016
[Data lake services can be made open sourced and public cloud-based.] Ground: A Data Context Service CIDR 2017 [Ground project]
[An interesting story about using text mining on tweets to understand emotion and sentiment.] Whoooaaa Duuuuude: Why We Stretch Words in Tweets and Texts WIRED
[Dr. Harry Shum, the ex EVP of Microsoft AI & Research Group, talked about how to read research articles. Please ignore the Chinese characters on the webpage as this talked was hosted by a Chinese social media Bilibili. The talk itself was in English] You are How You Read
[A new type of social media is emerging. In what aspects is it innovative?] How TikTok Is Rewriting the World? New York Times
[Behind the emerging social media is a novel type of economics.] The Passion Economy and the Future of Work Andreessen Horowitz (a16z)
[An interesting story about how William Farr developed the early data science about epidemics] How Data Became One of the Most Powerful Tools to Fight an Epidemic New York Times
[A small and simple idea to battle misinformation, but with a price tag in privacy] Twitter's Newest Trick Relies on Tracking Your Clicks WIRED
[Detecting bots in social media is task of information retrieval, machine learning and data mining. It may be harder than what people think.] Who’s a Bot? Who’s Not? New York Times
[How to run a big system in an unprecedentedly uncertain time? This is a case study.] Advancing Microsoft Teams on Azure—operating at pandemic scale Microsoft Blog
[Sports is an important and largely unexplored area for data mining] European Football Clubs Are Turning to AI for an Assist WIRED
[General search engines are still a place innovative start-up may emerge] A Former Google Executive Takes Aim at His Old Company With a Start-Up New York Times
[A nice data mining project on pandemic prediction] Can an Algorithm Predict the Pandemic’s Next Moves? New York Times
[Evaluation of user interest is challenging, particularly for streaming media] What Counts as a Streaming Hit? A Start-Up May Have Answers New York Times