Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Educational Tool for Learning about Social Media Tracking, Profiling, and Recommendation

Nicolas Pope, Juho Kahila, Jari Laru, Henriikka Vartiainen, Teemu Roos, Matti Tedre

TL;DR

The paper addresses the gap in practical tools for teaching the mechanisms of social media tracking, profiling, and recommendation to young learners. It presents Somekone, an educational tool with an Instagram-like interface, real-time visualizations, and GDPR-safe data handling that lets students observe how engagement shapes personal profiles and recommendations. The approach employs pair programming with live analytics and teacher-facing classroom visualizations to demystify algorithmic dynamics in social media. It argues that this explainable-AI driven, experiential method can foster data literacy, privacy awareness, and critical data mindsets, with potential for classroom adoption and policy guidance.

Abstract

This paper introduces an educational tool for classroom use, based on explainable AI (XAI), designed to demystify key social media mechanisms - tracking, profiling, and content recommendation - for novice learners. The tool provides a familiar, interactive interface that resonates with learners' experiences with popular social media platforms, while also offering the means to "peek under the hood" and exposing basic mechanisms of datafication. Learners gain first-hand experience of how even the slightest actions, such as pausing to view content, are captured and recorded in their digital footprint, and further distilled into a personal profile. The tool uses real-time visualizations and verbal explanations to create a sense of immediacy: each time the user acts, the resulting changes in their engagement history and their profile are displayed in a visually engaging and understandable manner. This paper discusses the potential of XAI and educational technology in transforming data and digital literacy education and in fostering the growth of children's privacy and security mindsets.

An Educational Tool for Learning about Social Media Tracking, Profiling, and Recommendation

TL;DR

The paper addresses the gap in practical tools for teaching the mechanisms of social media tracking, profiling, and recommendation to young learners. It presents Somekone, an educational tool with an Instagram-like interface, real-time visualizations, and GDPR-safe data handling that lets students observe how engagement shapes personal profiles and recommendations. The approach employs pair programming with live analytics and teacher-facing classroom visualizations to demystify algorithmic dynamics in social media. It argues that this explainable-AI driven, experiential method can foster data literacy, privacy awareness, and critical data mindsets, with potential for classroom adoption and policy guidance.

Abstract

This paper introduces an educational tool for classroom use, based on explainable AI (XAI), designed to demystify key social media mechanisms - tracking, profiling, and content recommendation - for novice learners. The tool provides a familiar, interactive interface that resonates with learners' experiences with popular social media platforms, while also offering the means to "peek under the hood" and exposing basic mechanisms of datafication. Learners gain first-hand experience of how even the slightest actions, such as pausing to view content, are captured and recorded in their digital footprint, and further distilled into a personal profile. The tool uses real-time visualizations and verbal explanations to create a sense of immediacy: each time the user acts, the resulting changes in their engagement history and their profile are displayed in a visually engaging and understandable manner. This paper discusses the potential of XAI and educational technology in transforming data and digital literacy education and in fostering the growth of children's privacy and security mindsets.
Paper Structure (7 sections, 5 figures)

This paper contains 7 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Design of the Tool
  3. Data Collection (Tracking)
  4. Profiling (Modeling)
  5. Recommendation
  6. Social network
  7. Discussion

Figures (5)

  • Figure 1: Children using Somekone on two devices: One for browsing the feed, one for analytics of the other. The classroom view shows a social network of the classroom.
  • Figure 2: A screenshot of Jarmo browsing images on Somekone on his phone, with "like" button showing the range of available emojis.
  • Figure 3: Anna is Jarmo's pair in the exercise, and her device is connected to Jarmo's device. Anna can choose between real-time views of all the data Jarmo's browsing generates, the profile Somekone has built of Jarmo, and the upcoming recommendations and verbal explanations for them ("because you liked...", "ranked high for taste similarity...", etc).
  • Figure 4: Social network of children browsing Somekone in the classroom (displayed on the classroom projector). Thick lines between nodes indicate a strong similarity in taste profile vectors. Nodes are clustered by the similarity of topic (tag) engagement, as indicated by their proximity and node color.
  • Figure 5: Three example views of the data (displayed on the classroom projector)