Analysis of readers’ engagement and text classification for an educational digital social reading activity on Twitter.
with Maurizio Toccu and Marco Viviani (University of Milan-Bicocca)
We analysed 16,000 tweets generated as part of a public social reading activity organised for high school students. We tested various techniques to detect text reuse (from the commented novel to the tweets), eventually using an algorithm employed for analysing DNA sequences (BLAST). We also reconstructed the network of interactions among all the users involved in the social reading.
R, tidyverse, quanteda, passim, BLAST
Text reuse detection, lexical complexity, regular expressions, TF-IDF, network analysis
Pianzola, Federico, Maurizio Toccu, and Marco Viviani. 2021 (in press). “Readers’ Engagement through Digital Social Reading on Twitter: The TwLetteratura Case Study”. Library Hi Tech.
Data and code: https://github.com/fedormyskin/MattiaTw