The SMOL Reading Group

Every story has a beginning. This post is the beginning of the SMOL Lab. The Social Media, Online behavior and Language Lab will be a wondrous place, studying online human behavior and computer mediated communication in ways big and small. One day, we'll have our own spiders, bots, crawlers, apps, and python (scripts). For now,...

The AAAI-2020 AffCon Workshop + CL-Aff Shared Task: Get it #offmychest

More details at https://sites.google.com/view/affcon2020/home See you in New York on Feb 7, 2020!!

Stats 101: Where to stat?

See what I did there? If you're anything like me, you're finding your way backwards into stats after spending a lifetime thinking that all there was to the field was mean, median, mode, sometimes cumulative frequency, and those are things you left behind in high school. Newsflash: not only is stats underlying every quantitative prediction...

Open tools for Natural Language Processing / NLProc / NLP

Liling Tan of Saarland University compiled a list of open source NLP tools for anyone to get started with. Thanks Liling! We don't know each other, but your list is awesome!   Here's the compiled list of NLP tools. Here are the NLP tools slides that Liling presented at FOSS Asia in 2017.

Guide to planning and analyzing experiments

I discovered this amazing tutorial on planning and analyzing experiments by Eytan Bakshy and Sean Taylor of Facebook research, and I'm so glad I found it while I was still designing my first experiment. This is an amazing, comprehensive resource that takes you from starting to think about experiment design, all the way to what...

Writing a peer review

Update: I got an ICWSM Reviewer Award this year -- Thanks ICWSM!I'm using this post as a running list of checkpoints for reviewers of computational social science and computer science conferences. But everything can be generalized to whichever field you belong to. Here's a short and sweet list of points to write your next peer...

The CL-Aff HappyDB dataset: in Pursuit of Happiness

It has long been known that human affect is context-driven, and that labeled datasets should account for these factors in generating predictive models of affect. This motivates our Shared Task, which is organized in collaboration with researchers at Megagon Labs and is built upon the HappyDB dataset, comprising human accounts of `happy moments'. I'll add...

Guide to choosing research methods & writing dissertations

I didn't have much help and jumped into the deep end when I started my PhD. Since then, I've had to unlearn a lot of practices, and pick up strategies from experienced seniors and colleagues. I'm going to use this post to collect some helpful links for anyone who needs a fresh start, or simply...