This research's main objective is to analyse Online Travel Reviews (OTRs) related to tourist attractions aiming at identifying recurring discussion topics/themes to infer whether travellers make reference to positive or negative experiences during their trips. This study focuses on the case of Guanajuato, a Mexican cultural destination. It is important to mention that similar analyses have not been carried out to study any Mexican destination so far. OTRs are analysed using two Natural Language Processing approaches: Mutual Information Ranking and Jaccard Coefficient. These are applied to quantify and extract the most representative themes and the main topics from each polarity within the OTRs. These techniques have been extensively studied in various areas, however, to the best of our knowledge, they have not been applied in digital tourism to detect essential issues during the travel experience. As a result, two recurrent negative themes/topics (‘cleanliness’, ‘prices’) were identified throughout this analysis. One surprising finding of this work relates to the lack of variation between national and international travellers' evaluations. The findings of this study contribute to confirming the role of OTRs within the contemporary tourist experience by identifying those places perceived negatively or positively directy from the visitors' perspective.

The goal of Author Profiling (AP) is to identify demographic aspects (e.g., age, gender) from a given set of authors by analyzing their written texts. Recently, the AP task has gained interest in many problems related to computer forensics, psychology, marketing, but specially in those related with social media exploitation. As known, social media data is shared through a wide range of modalities (e.g., text, images and audio), representing valuable information to be exploited for extracting valuable insights from users. Nevertheless, most of the current work in AP using social media data has been devoted to analyze textual information only, and there are very few works that have started exploring the gender identification using visual information. Contrastingly, this paper focuses in exploiting the visual modality to perform both age and gender identification in social media, specifically in Twitter. Our goal is to evaluate the pertinence of using visual information in solving the AP task. Accordingly, we have extended the Twitter corpus from PAN 2014, incorporating posted images from all the users, making a distinction between tweeted and retweeted images. Performed experiments provide interesting evidence on the usefulness of visual information in comparison with traditional textual representations for the AP task.

Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of two given texts: a semantically-informed similarity measure and a semantically-informed edit distance. Both measures are able to extract semantic information from either an external resource or a distributed representation of words, resulting in informative features for training a supervised classifier for detecting paraphrase plagiarism. Obtained results indicate that the proposed metrics are consistently good in detecting different types of paraphrase plagiarism. In addition, results are very competitive against state-of-the art methods having the advantage of representing a much more simple but equally effective solution.