I’m very pleased that we will be able to present a piece of research we have been working on for some time now at RecSys this year.

In my work on fair recommendation, one of the key questions I want to unravel is how recommender systems interact with issues of representation among content creators. As we work, as a society, to improve representation of historically underrepresented groups — women, racial minories, indigenous peoples, gender minorities, etc. — will recommender systems hinder those efforts? Will ‘get recommended to potential audiences’ be yet another roadblock in the path of authors from disadvantaged groups, or might the recommender aid in the process of exposing new creators to the audiences that will appreciate their work and make them thrive?

In this paper, we (myself, my students Mucun Tian and Imran Kazi, and my colleagues Hoda Mehrpouyan and Daniel Kluver) present our first results on this problem. This work, along with our work on recommender evaluation errors, formed the key preliminary results for my NSF CAREER proposal.

This paper has a few firsts for me. It’s my first fully-Bayesian paper, and is also the first time I have been able to provide complete code to reproduce the experiments and analysis with the manuscript submission.

You don’t know when the sad will fall. You can sometimes see it coming; like the water that falls on you from nowhere when you lie{:.hidden}, it has some predictability. Unlike the water, it does not afford much opportunity for control, and you never know quite what to expect. When you see it coming, you can brace for impact; with practice, put on the happy face and soldier on.

That’s the idea, anyway.

It hit like a tsunami a little after 7 pm. The date was August 30, 2017; the place a cafe on a side street in Como, Italy.

Online platforms take different approaches to moderating — or not — the content that can be published or discovered through their platforms. I discovered today that some of the GIF search engines are censoring certain search terms. So I decided to poke a little more and see what is happening.

So, I won the NSF CAREER award. To say I’m excited about this would be an understatement — my first Ph.D student has support locked in, I get to actually do the work I’ve been building towards for years now, and we’re going to have a much better understanding of how recommender systems (mis)behave in response to their individual and social human contexts.

One of the things I found useful while planning and writing was hearing a variety of ‘path-to-the-CAREER’ stories and trying to take from them the things that would work for me. So here’s mine, for what it is worth. There are many paths to success; the opening line of Anna Karenina does not apply to grantwriting. My road is neither necessary nor sufficient.

This post is adapted and heavily expanded from notes I wrote in preparation for the successful applicant panel at Boise State’s CAREER prep workshop this spring.

Over the years of teaching and research, I have gradually standardized the notation that I use for describing the math of recommender systems. This is the notation that I use in my classes, Joe Konstan and I have adopted for our MOOC, and that I use in most of my research papers. (And thanks to Joe for helping revise it to its current form.)

If you haven’t already settled on a notation, perhaps you would consider adopting this one. I also welcome feedback on improving it.