Datasets and Models for Authorship Attribution on Italian Personal Writings
This work addresses authorship attribution for Italian personal writings, providing insights into genre, topic, and gender effects, but it is incremental as it applies existing methods to new data.
The study tackled authorship verification on short Italian texts using two novel datasets, finding that verification is feasible with limited data but improves with more evidence, and that gender and topic can serve as indicative clues or overshadow personal style if not controlled.
Existing research on Authorship Attribution (AA) focuses on texts for which a lot of data is available (e.g novels), mainly in English. We approach AA via Authorship Verification on short Italian texts in two novel datasets, and analyze the interaction between genre, topic, gender and length. Results show that AV is feasible even with little data, but more evidence helps. Gender and topic can be indicative clues, and if not controlled for, they might overtake more specific aspects of personal style.