Search

Social media have become an integral part of our lives, expanding our interlinking capabilities to new levels. There is plenty to be said about their positive effects. On the other hand, however, some serious negative implications of social media have been repeatedly highlighted in recent years, pointing at various threats to society and its more vulnerable members, such as teenagers, in particular, ranging from much-discussed problems such as digital addiction and polarization to manipulative influences of algorithms and further to more teenager-specific issues (e.g., body stereotyping). The impact of social media—both at an individual and societal level—is characterized by the complex interplay between the users' interactions and the intelligent components of the platform. Thus, users' understanding of social media mechanisms plays a determinant role. We thus propose a theoretical framework based on an adaptive “Social Media Virtual Companion” for educating and supporting an entire community, teenage students, to interact in social media environments in order to achieve desirable conditions, defined in terms of a community-specific and participatory designed measure of Collective Well-Being (CWB). This Companion combines automatic processing with expert intervention and guidance. The virtual Companion will be powered by a Recommender System (CWB-RS) that will optimize a CWB metric instead of engagement or platform profit, which currently largely drives recommender systems thereby disregarding any societal collateral effect. CWB-RS will optimize CWB both in the short term by balancing the level of social media threats the users are exposed to, and in the long term by adopting an Intelligent Tutor System role and enabling adaptive and personalized sequencing of playful learning activities. We put an emphasis on experts and educators in the educationally managed social media community of the Companion. They play five key roles: (a) use the Companion in classroom-base

Natural language processing and other areas of artificial intelligence have seen staggering progress in recent years, yet much of this is reported with reference to somewhat limited benchmark datasets. We see the deployment of these techniques in realistic use cases as the next step in this development. In particular, much progress is still needed in educational settings, which can strongly improve users’ safety on social media. We present our efforts to develop multi-modal machine learning algorithms to be integrated into a social media companion aimed at supporting and educating users in dealing with fake news and other social media threats. Inside the companion environment, such algorithms can automatically assess and enable users to contextualize different aspects of their social media experience. They can estimate and display different characteristics of content in supported users’ feeds, such as ‘fakeness’ and ‘sentiment’, and suggest related alternatives to enrich users’ perspectives. In addition, they can evaluate the opinions, attitudes, and neighbourhoods of the users and of those appearing in their feeds. The aim of the latter process is to raise users’ awareness and resilience to filter bubbles and echo chambers, which are almost unnoticeable and rarely understood phenomena that may affect users’ information intake unconsciously and are unexpectedly widespread. The social media environment is rapidly changing and complex. While our algorithms show state-of-the-art performance, they rely on task-specific datasets, and their reliability may decrease over time and be limited against novel threats. The negative impact of these limits may be exasperated by users’ over-reliance on algorithmic tools. Therefore, companion algorithms and educational activities are meant to increase users’ awareness of social media threats while exposing the limits of such algorithms. This will also provide an educational example of the limits affecting the machine-learning compon

We describe our approach (MB-Courage team) in the Sexism Identification in Social Networks Shared Task (EXIST). We submitted three runs for each task, two of them based on Graph Convolutional Neural Networks (GCN) exploring different edge creation strategies and one combining graph embeddings from different GCN through ensemble methods. In addition, we explored different GCN models and text-to- graph strategies. We identified that in Task 2 the models take advantage of the syntactic relationship between words encoded in the graph, while it did not strongly impact Task 1. Moreover, the models generalized the task while maintaining similar (in some cases better) results in the social network that was not used in training. On average, our best models performed similarly across languages and social media, ranking 37th (out of 72 runs) for Task 1 and 40th (out of 63) for Task 2.

BACKGROUND: Intestinal ultrasound (IUS) is a valuable tool for assessment of Crohn's disease (CD). However, there is no widely accepted luminal disease activity index. AIMS: To identify appropriate IUS protocols, indices, items, and scoring methods for measurement of luminal CD activity and integration of IUS in CD clinical trials. METHODS: An expert international panel of adult and paediatric gastroenterologists (n = 15) and radiologists (n = 3) rated the appropriateness of 120 statements derived from literature review and expert opinion (scale of 1-9) using modified RAND/UCLA methodology. Median panel scores of 1 to ≤3.5, >3.5 to <6.5 and ≥6.5 to 9 were considered inappropriate, uncertain and appropriate ratings respectively. The statement list and survey results were discussed prior to voting. RESULTS: A total of 91 statements were rated appropriate with agreement after two rounds of voting. Items considered appropriate measures of disease activity were bowel wall thickness (BWT), vascularity, stratification and mesenteric inflammatory fat. There was uncertainty if any of the existing IUS disease activity indices were appropriate for use in CD clinical trials. Appropriate trial applications for IUS included patient recruitment qualification when diseased segments cannot be adequately assessed by ileocolonoscopy and screening for exclusionary complications. At outcome assessment, remission endpoints including BWT and vascularity, with or without mesenteric inflammatory fat, were considered appropriate. Components of an ideal IUS disease activity index were identified based upon panel discussions. CONCLUSIONS: The panel identified appropriate component items and applications of IUS for CD clinical trials. Empiric evidence, and development and validation of an IUS disease activity index are needed.

Hate Speech identification is a challenging task given the world knowledge required. Moreover, it is even more complex in the social media context due to language and media specificities. Despite these challenges, advances in this task may help improving collective well-being on social media. In this context, the biCourage team participated in the English version of Task 1 of HASOC 2021, a shared task for “Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages”. Our participation in this campaign aimed to examine the suitability of Graph Convolutional Neural Networks (GCN), due to their capability to integrate flexible contextual priors, as a computationally effective solution compared to more computationally expensive and relatively data-hungry methods, such as fine-tuning. Specifically, we explored and combined two text-to-graph strategies based on different language modelling objectives, comparing them with fine-tuned Bert. We submitted the results of several deep learning architectures, comprised of different arrangements of GCNs and transformer architectures. Our team achieved the best results in both subtasks using the GCNs based architectures combining two text-to-graph strategies ranked in 21st and 20th positions in Subtasks 1A and 1B. Assessing the models’ prediction, we identify complementary capabilities in the text-to-graph strategies that further research on their combination can explore. Moreover, the proposed GCN model is 3.85 times faster than fine-tuned Bert in training speed and still outperforms it by 2.3% and 5.41% on the F1 score of Subtasks 1A and 1B, respectively.

Automatic text simplification is an active research area, and there are first systems for English, Spanish, Portuguese, and Italian. For German, no data-driven approach exists to this date, due to a lack of training data. In this paper, we present a parallel corpus of news items in German with corresponding simplifications on two complexity levels. The simplifications have been produced according to a well-documented set of guidelines. We then report on experiments in automatically simplifying the German news items using state-of-the-art neural machine translation techniques. We demonstrate that despite our small parallel corpus, our neural models were able to learn essential features of simplified language, such as lexical substitutions, deletion of less relevant words and phrases, and sentence shortening.