Viral marketing is one of the techniques most used by companies to increase their reach_x000D_ and improve their pro ts. This technique is carried out through the Influencers, people who_x000D_ because of their ability to persuade very high on their followers, are in charge of viralizing_x000D_ what they want to promote. However, knowing which Influencers are the ideals for each_x000D_ target audience is not a trivial process, since determining those users is subject to a set of_x000D_ criteria beyond the simple popularity of them. One way that organizations currently use is the suscription to online Influencers detection services, however, these services have a high cost and are not very transparent to users, who do not know the criteria under which they are being determined. This thesis proposes a Methodology for the Detection of In_x000D_ uencers on Twitter,_x000D_ which follows the f...

BERT produces state-of-the-art solutions for many natural language processing tasks at the cost of interpretability. As works discuss the value of BERT’s attention weights to this purpose, we contribute with an attention-based interpretability framework to identify the most influential words for stance classification using BERT-based models. Unlike related work, we develop a broader level of interpretability focused on the overall model behavior instead of single instances. We aggregate tokens’ attentions into words’ attention weights that are more meaningful and can be semantically related to the domain. We propose attention metrics to assess words’ influence in the correct classification of stances. We use three case studies related to COVID-19 to assess the proposed framework in a broad experimental setting encompassing six datasets and four BERT pre-trained models for Portugu...