Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddings of sentences labelled as semantically similar by annotators.Since big labelled datasets are rare, in particular for non-English languages, and expensive, recent studies focus on unsupervised approaches that require not-paired input sentences.We instead propose a language-independent approach to build large datasets of pairs of informal texts weakly similar, without manual human effort, exploiting Twitter's intrinsic powerful signals of relatedness: replies and quotes of tweets.We use the collected pairs to train a Transformer model with triplet-like structures, and we test the generated embeddings on Twitter NLP similarity tasks (PIT and TURL) and STSb.We also introduce four new sentence ranking evaluation benchmarks of informal texts, carefully extracted from the initial collections of tweets, proving not only that our best model learns classical Semantic Textual Similarity, but also excels on tasks where pairs of sentences are not exact paraphrases.Ablation studies reveal how increasing the corpus size influences positively the results, even at 2M samples, suggesting that bigger collections of Tweets still do not contain redundant information about semantic similarities.1

Social networks are huge continuous sources of information that can be used to analyze people's behavior and thoughts. Our goal is to extract such information and predict political inclinations of users. In particular, this paper investigates the importance of syntactic features of texts written by users in the process.Our hypothesis is that people belonging to the same political party write in similar ways, thus they can be classified properly on the basis of the words that they use. We analyze tweets because Twitter is commonly used in Italy for discussing about politics; moreover, it provides an official API that can be easily exploited for data extraction.Many classifiers were applied to different kinds of features and NLP vectorization methods in order to obtain the best method capable of confirming our hypothesis. To evaluate their accuracy, a set of current Italian deputies with consistent activity in Twitter has been selected as ground truth, and we have then predicted their political party. Using the results of our analysis, we also got interesting insights into current Italian politics.