Computational Linguistics in the Netherlands Journal 4 (2014) Submitted 06/2014; Published 12/2014 Gender Recognition on Dutch Tweets Hans van Halteren Nander Speerstra Radboud University Nijmegen, CLS, Linguistics Abstract In this paper, we investigate gender recognition on Dutch Twitter material, using a corpus consisting of the full Tweet production (as far as present in the Twi NL data set) of 600 users (known to be human individuals) over 2011 and We experimented with several authorship profiling techniques and various recognition features, using Tweet text only, in order to determine how well they could distinguish between male and female authors of Tweets.
We achieved the best results, 95.5% correct assignment in a 5-fold cross-validation on our corpus, with Support Vector Regression on all token unigrams.
But before you start thinking this is entirely about looks, do not fret!Then we describe our experimental data and the evaluation method (Section 3), after which we proceed to describe the various author profiling strategies that we investigated (Section 4). Gender Recognition Gender recognition is a subtask in the general field of authorship recognition and profiling, which has reached maturity in the last decades(for an overview, see e.g. Even so, there are circumstances where outright recognition is not an option, but where one must be content with profiling, i.e.Then follow the results (Section 5), and Section 6 concludes the paper. For whom we already know that they are an individual person rather than, say, a husband and wife couple or a board of editors for an official Twitterfeed. the identification of author traits like gender, age and geographical background.For our experiment, we selected 600 authors for whom we were able to determine with a high degree of certainty a) that they were human individuals and b) what gender they were.We then experimented with several author profiling techniques, namely Support Vector Regression (as provided by LIBSVM; (Chang and Lin 2011)), Linguistic Profiling (LP; (van Halteren 2004)), and Ti MBL (Daelemans et al.2009) managed to increase the gender recognition quality to 89.2%, using sentence length, 35 non-dictionary words, and 52 slang words.The authors do not report the set of slang words, but the non-dictionary words appear to be more related to style than to content, showing that purely linguistic behaviour can contribute information for gender recognition as well.In this paper we restrict ourselves to gender recognition, and it is also this aspect we will discuss further in this section.A group which is very active in studying gender recognition (among other traits) on the basis of text is that around Moshe Koppel. 2002) they report gender recognition on formal written texts taken from the British National Corpus (and also give a good overview of previous work), reaching about 80% correct attributions using function words and parts of speech.The resource would become even more useful if we could deduce complete and correct metadata from the various available information sources, such as the provided metadata, user relations, profile photos, and the text of the tweets.In this paper, we start modestly, by attempting to derive just the gender of the authors 1 automatically, purely on the basis of the content of their tweets, using author profiling techniques.