Michael S. Bernstein

TL;DR: This paper used natural language processing with a crowdsourced lexicon of stereotypes to capture gender biases in fiction and found that male overrepresentation and traditional gender stereotypes are common throughout nearly every genre in the corpus.

TL;DR: The authors report an online experiment that changes participants' pseudonyms as they appear to collaborators, temporarily masking a jury's awareness that they have deliberated together before, which allows them to measure consistency by reconvening the same jury on similar cases.

TL;DR: In an evaluation of end-user audits on a popular comment toxicity model with 17 non-technical participants, participants both replicated issues that formal audits had previously identified and also raised previously underreported issues such as under-flagged on veiled forms of hate that perpetuate stigma and over-flagging of slurs that have been reclaimed by marginalized communities.

TL;DR: Model sketching as mentioned in this paper is a framework for iteratively and rapidly authoring functional approximations of a machine learning model's decision-making logic, which refocuses practitioner attention on composing high-level, human-understandable concepts that the model is expected to reason over (e.g., profanity, racism, or sarcasm in a content moderation task).

TL;DR: This work introduces MyriadHub, a mail client where users start conversations and then crowd workers extract underlying conversational patterns and rules to accelerate responses to future similar emails, and introduces techniques that exploit similarities across conversations to recycle relevant parts of previous conversations.