Social Media are sensors in the real world that can be used to measure the pulse of societies. However, the massive and unfiltered feed of messages posted in social media is a phenomenon that nowadays raises social alarms, especially when these messages contain hate speech targeted to a specific individual or group. In this context, governments and non-governmental organizations (NGOs) are concerned about the possible negative impact that these messages can have on individuals or on the society. In this paper, we present HaterNet, an intelligent system currently being used by the Spanish National Office Against Hate Crimes of the Spanish State Secretariat for Security that identifies and monitors the evolution of hate speech in Twitter. The contributions of this research are many-fold: (1) It introduces the first intelligent system that monitors and visualizes, using social network analysis techniques, hate speech in Social Media. (2) It introduces a novel public dataset on hate speech in Spanish consisting of 6000 expert-labeled tweets. (3) It compares several classification approaches based on different document representation strategies and text classification models. (4) The best approach consists of a combination of a LTSM+MLP neural network that takes as input the tweet’s word, emoji, and expression tokens’ embeddings enriched by the tf-idf, and obtains an area under the curve (AUC) of 0.828 on our dataset, outperforming previous methods presented in the literature.

This paper focuses on the issue of intimate partner violence and, specifically, on the distribution of femicides over time and the existence of copycat effects. This is the subject of an ongoing debate often triggered by the social alarm following multiple intimate partner homicides (IPHs) occurring in a short span of time. The aim of this research is to study the evolution of IPHs and provide a far-reaching answer by rigorously analyzing and searching for patterns in data on femicides. The study analyzes an official dataset, provided by the system VioGén of the Secretaría de Estado de Seguridad (Spanish State Secretariat for Security), including all the femicides occurred in Spain in 2007-2017. A statistical methodology to identify temporal interdependencies in count time series is proposed and applied to the dataset. The same methodology can be applied to other contexts. There has been a decreasing trend in the number of femicides per year. No interdependencies among the temporal distribution of femicides are observed. Therefore, according to data, the existence of copycat effect in femicides cannot be claimed. Around 2011 there was a clear change in the average number of femicides which has not picked up. Results allow for an informed answer to the debate on copycat effect in Spanish femicides. The planning of femicides prevention activities should not be a reaction to a perceived increase in their occurrence. As a copycat effect is not detected in the studied time period, there is no evidence supporting the need to censor media reports on femicides.

Identifying bots on X (formerly Twitter) is essential for preventing misinformation and ensuring user safety. However, current models face several challenges: (i) the use of outdated techniques and attributes, particularly those trained on older datasets; (ii) reproducibility problems stemming from unique and insufficiently detailed methodologies; (iii) shallow analysis depth, with few studies investigating all combinations of feature-based, text-based, and graph-based methods; (iv) a lack of thorough literature reviews to pinpoint effective characteristics for future research. To overcome these gaps, this study proposes a novel multimodal bot detection framework which integrates user profile features, text analysis, and graph-based techniques. Utilizing the recent TwiBot-22 dataset, the model combines semantic text information from user profiles and tweets with graph representations of user interactions, including novel relationships like list ownership and all applicable user profile features, encompassing both those previously used in state-of-the-art models and newly introduced features designed to enhance detection accuracy. The study compares the proposed model against existing approaches and demonstrates a significant improvement in detection accuracy, exceeding the best-performing models by 5.48%. The research contributes a comprehensive evaluation of feature sets, highlights the advantages of incorporating multiple detection strategies, and identifies key parameters for optimizing bot detection models.