CLiPS Stylometry Investigation (CSI) corpus: A Dutch corpus for the detection of age, gender, personality, sentiment and deception in text

By Ben Verhoeven, Walter Daelemans. 2014

71 citations recorded by the source corpus.

We present the CLiPS Stylometry Investigation (CSI) corpus, a new Dutch corpus containing reviews and essays written by university students. It is designed to serve multiple purposes: detection of age, gender, authorship, personality, sentiment, deception, topic and genre. Another major advantage is its planned yearly expansion with each year’s new students. The corpus currently contains about 305,000 tokens spread over 749 documents. The average review length is 128 tokens; the average essay length is 1126 tokens. The corpus will be made available on the CLiPS website (www.clips.uantwerpen.be/datasets) and can freely be used for academic research purposes. An initial deception detection experiment was performed on this data. Deception detection is the task of automatically classifying a text as being either truthful or deceptive, in our case by examining the writing style of the author. This task has never been investigated for Dutch before. We performed a supervised machine learning experiment using the SVM algorithm in a 10-fold cross-validation setup. The only features were the token unigrams present in the training data. Using this simple method, we reached a state-of-the-art F-score of 72.2%.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Exploiting Unintended Feature Leakage in Collaborative Learning (2018, background): “lds 528,878 check-ins. The model is a gender classifier, a task previously studied by Pang et al. [37] on similar datasets. CLiPS Stylometry Investigation (CSI) Corpus. This annually expanded dataset [51] contains student-written essays and reviews. The 1,412 reviews are equally split between Truthf”
Adversarial Removal of Demographic Attributes from Text Data (2018, background): “It is well established that textual information can be predictive of age, race, gender, and many other social factors of the author (Koppel et al., 2002; Burger et al., 2011; Nguyen et al., 2013; Weren et al., 2014; Verhoeven and Daelemans, 2014; Rangel et al., 2016; Verhoeven et al., 2016; Blodgett”
Membership Inference Attacks on Machine Learning: A Survey (2021, unknown): “Text Data Classification CSI [203] 1,412 N.”
Inference Attacks Against Collaborative Learning (2018, background): “This annually expanded dataset [51] contains student-written essays and reviews.”
A Survey of Privacy Attacks in Machine Learning (2020, methodology): “CLiPS stylometry [94] text binary classification [61] 1,412 reviews”
(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas (2019, background): “PASTEL can be used in many style related applications including style classiﬁcation, stylome-try (Verhoeven and Daelemans, 2014), style transfer (Fu et al., 2018), visually-grounded style transfer, and more.”
Deception detection in Russian texts (2017, background): “We are aware of only two other resources for deception detection where demographic data is available (Prez-Rosas and Mihalcea, 2014; Verhoeven and Daelemans, 2014).”