The article describes a model of automatic interpretation of English puns, based on Roget's Thesaurus, and its implementation, PunFields. In a pun, the algorithm discovers two groups of words that belong to two main semantic fields. The fields become a semantic vector based on which an SVM classifier learns to recognize puns. A rule-based model is then applied for recognition of intentionally ambiguous (target) words and their definitions. In SemEval Task 7 PunFields shows a considerably good result in pun classification, but requires improvement in searching for the target word and its definition.

No abstract

The Internet is a communication space where newly formed communities search for ways to reflect on their social nature. We provide a theoretical background to demonstrate how the humor was used to manipulate social groups before the rise of mass media and after it. We use Critical Discourse Analysis and pragmatics to study several cases of social manipulation with the help of humor. The two Internet communities, 2ch and Pikabu, being among the largest Russian-speaking entertainment communities, often compete and use humor as a way to manipulate their representatives for social purposes: to consolidate, fight back, reflect on their community's norms and values. Our research shows that these communities follow the old traditions of humor and laughter to organize the poorly regulated information space. Although 2chers tend to use trolling more often, there are no general differences between these communities in how they use humor to manipulate their social group.

Being a matter of cognition, user interests should be apt to classification independent of the language of users, social network and content of interest itself. To prove it, we analyze a collection of English and Russian Twitter and Vkontakte community pages by interests of their followers. First, we create a model of Major Interests (MaIs) with the help of expert analysis and then classify a set of pages using machine learning algorithms (SVM, Neural Network, Naive Bayes, and some other). We take three interest domains that are typical of both English and Russian-speaking communities: football, rock music, vegetarianism. The results of classification show a greater correlation between Russian-Vkontakte and Russian-Twitter pages while English-Twitter pages appear to provide the highest score.

No abstract