This article presents our approach for detecting a target of offensive messages in Twitter, including Individual, Group and Others classes. The model we have created is an ensemble of simpler models, including Logistic Regression, Naive Bayes, Support Vector Machine and the interpolation between Logistic Regression and Naive Bayes with 0.25 coefficient of interpolation. The model allows us to achieve 0.547 macro F1-score.

With the constant increase in the amount of information available in online communities, the task of building an appropriate Recommender System to support the user in her decision making process is becoming more and more challenging. In addition to the classical collaborative filtering and content based approaches, taking into account ratings, preferences and demographic characteristics of the users, a new type of Recommender System, based on personality parameters, has been emerging recently. In this paper we describe the TWIN (Tell Me What I Need) Personality Based Recommender System, and report on our experiments and experiences of utilizing techniques which allow the extraction of the personality type from text (following the Big Five model popular in the psychological research). We estimate the possibility of constructing the personality-based Recommender System that does not require users to fill in personality questionnaires. We are applying the proposed system in the online travelling domain to perform TripAdvisor hotels recommendation by analysing the text of user generated reviews, which are freely accessible from the community website.

Subjectivity analysis and authorship attribution are very popular areas of research. However, work in these two areas has been done separately. We believe that by combining information about subjectivity in texts and authorship, the performance of both tasks can be improved. In the paper a personalized approach to opinion mining is presented, in which the notions of personal sense and idiolect are introduced; the approach is applied to the polarity classification task. It is assumed that different authors express their private states in text individually, and opinion mining results could be improved by analyzing texts by different authors separately. The hypothesis is tested on a corpus of movie reviews by ten authors. The results of applying the personalized approach to opinion mining are presented, confirming that the approach increases the performance of the opinion mining task. Automatic authorship attribution is further applied to model the personalized approach, classifying documents by their assumed authorship. Although the automatic authorship classification imposes a number of limitations on the dataset for further experiments, after overcoming these issues the authorship attribution technique modeling the personalized approach confirms the increase over the baseline with no authorship information used.