Personality extraction through social networks is a field that only recently started to capture the attention of researchers. The task consists in, starting with a corpus of user profiles on a particular social network, classifying their personalities correctly, according to a specific personality model as described in psychology. In this master thesis, three innovations to the domain are presented. Firstly, the collection of a corpus of LinkedIn users. Secondly, the extraction of the personality according to two personality models, DiSC and MBTI, the extraction with DiSC having never been done before. Lastly, the idea of going from one personality model to the other is explored, thus creating the possibility of having the results on two personality models with only one personality test.

Membership Query Synthesis (MQS) is an active learning paradigm in which one labels generated artificial examples instead of genuine ones to extend a dataset. Despite prodigious advances in the power of generative models, an essential component of MQS, the field stays severely under-studied, especially in the textual domain. We found only one other paper, which selects examples in a latent space close to the decision boundary and shows good results on a curated dataset of short sentences. We show that this performs poorly when used on a real dataset. We propose and report better results than random selection of unlabelled genuine data with random generation of artificial data from a variational auto-encoder coupled with a simple set of filtering mechanisms. This provides an improvement of 31.1% over the previous MQS state-of-the-art on the SST-2 dataset, and of 2.7% over random active learning. To the best of our knowledge, this is the first time MQS is reported to work on a textual task with no constraint on the size of the input sentences.