The following is a descriptive and network analysis of ACM RecSys 2022 conference participant interactions on Twitter.

General statistics

During the two weeks of data collection (from 09/12 to 09/25), at least 2,289 tweets were posted (with the hashtags #RecSys2022 or #RecSys22, or directly referencing the @ACMRecSys account), an increase of 8.9% over last year.

The most prolific and active person on Twitter during RecSys was Manel Slokom, who was sharing content about countless talks and presentations she attended. Thanks Manel! 👏

On the other hand, the 2 most tagged accounts were @FAccTRec and @craig_macdonald, respectively, for the workshop that was trending on Friday, and for the person (Craig Macdonald) that everyone wanted to talk to during the conference 😁.

We have a clear winner for the most loved person (with the most likes on Twitter) during RecSys2022 and that is Dr. Jen Golbeck.

By the way, she also has the most famous tweet from the conference. More than 350 likes. Well done 👍

How does TikTok know my location when I don’t have location access turned on for it? I’m visiting Seattle for #RecSys2022 & when posting a video of my dog, noticed it had my location as a suggestion. Checked settings and there isn’t even an option to allow location for TikTok 1/ pic.twitter.com/QMsZDKIKAw

— Dr. Jen Golbeck 🇺🇦💉x4 (@jengolbeck) September 19, 2022

Content statistics

The most used hashtags (not taking into account RecSys2022, which was used in at least 1462 tweets), are:

And the most used bigrams by RecSys2022 participants in their tweets, are:

However, if you want to know what the RecSys 2022 trend has been day by day, you can find it in the following 2 bar chart races.

Network analysis

Finally, a directed weighted graph, constructed from the interactions between RecSys 2022 participants with each other on Twitter (i.e., mentions, tagging, responses, etc.).

Code

For more information on this visual analysis, please refer to the following jupyter notebook.

Disclaimer

Neither the Twitter accounts nor the content of the tweets are used for profit. Only general statistics are calculated about them and shared with the RecSys community.

Contributing and Feedback

Any kind of feedback/suggestions would be greatly appreciated (algorithm design, documentation, improvement ideas, spelling mistakes, etc…). If you want to make a contribution to the course you can do it through a PR.

Author

• Created by Andrés Segura-Tinoco
• Updated on Sep 26, 2022

License

This project is licensed under the terms of the MIT license.