# A comparison of several AI techniques for authorship attribution on Romanian texts

arXiv: https://arxiv.org/abs/2211.05180 · HTML: https://mlsanity.com/paper/2211.05180/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 88 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 5 of 5)

- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [The Importance of Suppressing Domain Style in Authorship Analysis](https://mlsanity.com/paper/2005.14714/) (2020)
- [The Topic Confusion Task: A Novel Scenario for Authorship Attribution](https://mlsanity.com/paper/2104.08530/) (2021)
- [Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?](https://mlsanity.com/paper/1902.08939/) (2019)
- [Multi Expression Programming for solving classification problems](https://mlsanity.com/paper/2203.13202/) (2022)

## Built on by (most cited first, 4 of 4)

- [Trends and Challenges in Authorship Analysis: A Review of ML, DL, and LLM Approaches](https://mlsanity.com/paper/2505.15422/) (2025)
- [BERT-based Authorship Attribution on the Romanian Dataset called ROST](https://mlsanity.com/paper/2301.12500/) (2023)
- [Oldies but Goldies: The Potential of Character N-grams for Romanian Texts](https://mlsanity.com/paper/2506.15650/) (2025)
- [CHiPS: Character Histograms and Positional Signals for Lightweight Authorship Attribution in Romanian Texts](https://mlsanity.com/paper/2607.22884/) (2026)

## Abstract (arXiv)

Determining the author of a text is a difficult task. Here we compare multiple AI techniques for classifying literary texts written by multiple authors by taking into account a limited number of speech parts (prepositions, adverbs, and conjunctions). We also introduce a new dataset composed of texts written in the Romanian language on which we have run the algorithms. The compared methods are Artificial Neural Networks, Support Vector Machines, Multi Expression Programming, Decision Trees with C5.0, and k-Nearest Neighbour. Numerical experiments show, first of all, that the problem is difficult, but some algorithms are able to generate decent errors on the test set.