Your Mouse Reveals Your Gender and Age


listen on castbox.fmlisten on google podcastslisten on player.fmlisten on pocketcastslisten on podcast addictlisten on tuninlisten on Amazon Musiclisten on Stitcher

--:--
--:--


2022-11-28

Your Mouse Reveals your Gender and Age

Luis Leiva is a Professor of Computer Science at the University of Luxembourg. His research lies in an intersection of human computer interaction and machine learning. Today, he talks to us about his recent work on behavioural profiling via mouse tracking.

Luis began by explaining why there is a need to model user behavior. He outlined the techniques used for tracking human behavior on the web (eye gaze measurement and mouse tracking) and contrasted between both techniques. He particularly discussed why mouse tracking is preferable.

Luis then discussed how webpages track mouse movements of users. He spoke about the privacy concerns involved and the kind of data that can be inferred from mouse movements. Luis then talked about his research, where he and his co-authors tracked a sample of the user’s mouse movement after consent. He discussed some of the parameters they predicted such as the user’s attention, age, gender and so on. With five lines of code, he revealed the level of accuracy their predictive model had.

Luis spoke about the possibility of using the tracked user attention to determine whether an advertiser pays for an ad. The positives and negatives of accurate mouse tracking for targeted ads were also discussed on the show

Luis discussed efforts to curtail the privacy concerns with mouse tracking. Chrome privacy budget is one of such examples. Noise could also be intentionally added to the data so as to not give away completely accurate user information. Extensions such as FakerJS can be used for this.

Rounding up, Luis discussed other interesting lines of research in HCI and predicted the advancement in the field in the next 5 years. He spoke about the European research project, Symbiosis Project, where you can follow up on other similar research in HCI.

Luis A. Leiva

Luis A. Leiva is a professor of Computer Science at the University of Luxembourg, where he leads the Computational Interaction research group. He is the co-founder and former CTO of Sciling, an SME agency specialized in B2B Machine Learning solutions. His research interests lie at the intersection of Human-Computer Interaction and Machine Learning. His main research area is computational interaction, where he combines computational thinking with data-driven models and methods to enable, explain, and support user interaction.


Thanks to our sponsors for their support

Astrato is a modern BI and analytics platform built for the Snowflake Data Cloud. A next-generation live query data visualization and analytics solution, empowering everyone to make live data decisions.
https://astrato.io