The use of irony and sarcasm has been proven to be a pervasive phenomenon in social media posing a challenge to sentiment analysis systems. Such devices, in fact, can influence and twist the polarity of an utterance in different ways. A new dataset of over 10,000 tweets including a high variety of figurative language types, manually annotated with sentiment scores, has been released in the context of the task 11 of SemEval-2015.In this paper, we propose an analysis of the tweets in the dataset to investigate the open research issue of how separated figurative linguistic phenomena irony and sarcasm are, with a special focus on the role of features related to the multi-faceted affective information expressed in such texts. We considered for our analysis tweets tagged with #irony and #sarcasm, and also the tag #not, which has not been studied in depth before. A distribution and correlation analysis over a set of features, including a wide variety of psycholinguistic and emotional features, suggests arguments for the separation between irony and sarcasm. The outcome is a novel set of sentiment, structural and psycholinguistic features evaluated in binary classification experiments. We report about classification experiments carried out on a previously used corpus for #irony vs #sarcasm. We outperform in terms of F-measure the state-of-the-art results on this dataset. Overall, our results confirm the difficulty of the task, but introduce new datadriven arguments for the separation between #irony and #sarcasm. Interestingly, #not 1 Corresponding author: sulis@di.unito.it. 2 The first two authors equally contributed to this work.

The number of communications and messages generated by users on social media platforms has progressively increased in the last years. Therefore, the issue of developing automated systems for a deep analysis of users' generated contents and interactions is becoming increasingly relevant. In particular, when we focus on the domain of online political debates, interest for the automatic classification of users' stance towards a given entity, like a controversial topic or a politician, within a polarized debate is significantly growing. In this paper we propose a new model for stance detection in Twitter, where authors' messages are not considered in isolation, but in a diachronic perspective for shedding light on users' opinion shift dynamics along the temporal axis. Moreover, different types of social network community, based on retweet, quote, and reply relations were analyzed, in order to extract network-based features to be included in our stance detection model. The model has been trained and evaluated on a corpus of Italian tweets where users were discussing on a highly polarized debate in Italy, i.e. the 2016 referendum on the reform of the Italian Constitution. The development of a new annotated corpus for stance is described. Analysis and classification experiments show that network-based features help in detecting stance and confirm the importance of modeling stance in a diachronic perspective.

No abstract

We report on a data-driven investigation aimed at understanding the dynamics of message spreading in a real-world dynamical network of human proximity. We use data collected by means of a proximity-sensing network of wearable sensors that we deployed at three different social gatherings, simultaneously involving several hundred individuals. We simulate a message spreading process over the recorded proximity network, focusing on both the topological and the temporal properties. We show that by using an appropriate technique to deal with the temporal heterogeneity of proximity events, a universal statistical pattern emerges for the delivery times of messages, robust across all the data sets. Our results are useful to set constraints for generic processes of data dissemination, as well as to validate established models of human mobility and proximity that are frequently used to simulate realistic behaviors.

Abstract-The present work investigates the structural and dynamical properties of aNobii 1 , a social bookmarking system designed for readers and book lovers. Users of aNobii provide information about their library, reading interests and geographical location, and they can establish typed social links to other users. Here, we perform an in-depth analysis of the system's social network and its interplay with users' profiles. We describe the relation of geographic and interest-based factors to social linking. Furthermore, we perform a longitudinal analysis to investigate the interplay of profile similarity and link creation in the social network, with a focus on triangle closure. We report a reciprocal causal connection: profile similarity of users drives the subsequent closure in the social network and, reciprocally, closure in the social network induces subsequent profile alignment. Access to the dynamics of the social network also allows us to measure quantitative indicators of preferential linking.