Abstract
The rise of online social networks has reshaped the way information is published and spread. Users can now post in an effortless way and in any location, making this medium ideal for searching breaking news and journalistic relevant content. However, due to the overwhelming number of posts published every second, such content is hard to trace. Thus, it is important to develop methods able to detect and analyze whether a certain text contains journalistic relevant information. Furthermore, it is also important that this detection system can provide additional information towards a better comprehension of the prediction made. In this work, we overview our system, based on an ensemble classifier that is able to predict if a certain post is relevant from a journalistic perspective which outperforms the previous relevant systems in their original datasets. In addition, we describe REMINDS: a web platform built on top of our relevance system that is able to provide users with the visualization of the system's features as well as additional information on the text, ultimately leading to a better comprehension of the system's prediction capabilities. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the CENTERIS -International Conference on ENTERprise Information Systems / ProjMAN - International Conference on Project MANagement / HCist - International Conference on Health and Social Care Information Systems and Technologies.

Abstract
Social networks have provided the means for constant connectivity and fast information dissemination. In addition, real-time posting allows a new form of citizen journalism, where users can report events from a witness perspective. Therefore, information propagates through the network at a faster pace than traditional media reports it. However, relevant information is a small percentage of all the content shared. Our goal is to develop and evaluate models that can automatically detect journalistic relevance. To do it, we need solid and reliable ground truth data with a significantly large quantity of annotated posts, so that the models can learn to detect relevance over all the spectrum. In this article, we present and confront two different methodologies: an automatic and a human approach. Results on a test data set labelled by experts' show that the models trained with automatic methodology tend to perform better in contrast to the ones trained using human annotated data.

Abstract
In this article we discuss how social tagging can be used to improve the methodology used for clustering evaluation. We analyze the impact of the integration of tags in the clustering process and its effectiveness. Following the semiotic theory, the own nature of tags allows the reflection of which ones should be considered depending on the interpretant (community of users, or tag writer). Using a case with the community of users as the interpretant, our novel clustering algorithm (k-C), which is based on community detection on a network of tags, was compared with the standard k-means algorithm. The results indicate that the k-C algorithm created more effective clusters. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
The emergence of online social networks provided users with an easy way to publish and disseminate content, reaching broader audiences than previous platforms (such as blogs or personal websites) allowed. However, malicious users started to take advantage of these features to disseminate unreliable content through the network like false information, extremely biased opinions, or hate speech. Consequently, it becomes crucial to try to detect these users at an early stage to avoid the propagation of unreliable content in social networks’ ecosystems. In this work, we introduce a methodology to extract large corpus of unreliable posts using Twitter and two databases of unreliable websites (OpenSources and Media Bias Fact Check). In addition, we present an analysis of the content and users that publish and share several types of unreliable content. Finally, we develop supervised models to classify a twitter account according to its reliability. The experiments conducted using two different data sets show performance above 94% using Decision Trees as the learning algorithm. These experiments, although with some limitations, provide some encouraging results for future research on detecting unreliable accounts on social networks. © 2020, Springer Nature Switzerland AG.

Abstract

Abstract