Back

Matchathon: A guide to student-faculty connections in PhD programs

Amemiya, H. M.; Lapp, Z.; Smith, C. S.; Durdan, M. M.; DiMondo, M.; Bodiya, B.; Barolo, S.

2020-11-07 scientific communication and education
10.1101/2020.11.06.371526 bioRxiv
Show abstract

Relevant and impactful mentors are essential to a graduate students career. Finding mentors can be challenging in umbrella programs with hundreds of faculty members. To foster connections between potential mentors and students with similar research interests, we created a Matchathon event, which has successfully enabled students to find mentors. We developed an easy-to-use R Shiny app (https://github.com/UM-OGPS/matchathon/) to facilitate matching and organizing the event that can be used at any institution. It is our hope that this resource will improve the environment and retention rates for students in the academy. The open source app is publicly available on the web (app: https://UM-OGPS.shinyapps.io/matchathon/; source code: https://github.com/UM-OGPS/matchathon/).

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.