@article{van Halteren_2015, title={Metadata Induction on a Dutch Twitter Corpus: Initial phases}, volume={5}, url={https://clinjournal.org/clinj/article/view/56}, abstractNote={<p>In this paper, I pose that metadata induction for the TwiNL collection of Dutch tweets should start at a fundamental level, for which I address three types of classification. Identification of users tweeting predominantly in Dutch is shown to be possible with an F-value over 98%. For the identification of individual humans (as opposed to e.g. groups or bots), no classifier is tested, but a number of useful text-based measurements are presented. Finally, the identification of children of school-going age (by far the largest user group in the collection) is shown to be possible on the basis of just unigram counts with high accuracy (93.5%), increasing to very high accuracy (97%) when at least 1,000 tweets are available.</p>}, journal={Computational Linguistics in the Netherlands Journal}, author={van Halteren, Hans}, year={2015}, month={Nov.}, pages={37–48} }