Abstract
Social media platforms are used to discuss current events with very complex narratives that become difficult to understand. In this work, we introduce Tweet2Story, a web app to automatically extract narratives from small texts such as tweets and describe them through annotations. By doing this, we aim to mitigate the difficulties existing on creating narratives and give a step towards deeply understanding the actors and their corresponding relations found in a text. We build the web app to be modular and easy-to-use, which allows it to easily incorporate new techniques as they keep getting developed.

Abstract

Abstract
Topics discussed on social media platforms contain a disparate amount of information written in colloquial language, making it difficult to understand the narrative of the topic. In this paper, we take a step forward, towards the resolution of this problem by proposing a framework that performs the automatic extraction of narratives from a document, such as tweet posts. To this regard, we propose a methodology that extracts information from the texts through a pipeline of tasks, such as co-reference resolution and the extraction of entity relations. The result of this process is embedded into an annotation file to be used by subsequent operations, such as visualization schemas. We named this framework Tweet2Story and measured its effectiveness under an evaluation schema that involved three different aspects: (i) as an Open Information extraction (OpenIE) task, (ii) by comparing the narratives of manually annotated news articles linked to tweets about the same topic and (iii) by comparing their knowledge graphs, produced by the narratives, in a qualitative way. The results obtained show a high precision and a moderate recall, on par with other OpenIE state-of-the-art frameworks and confirm that the narratives can be extracted from small texts. Furthermore, we show that the narrative can be visualized in an easily understandable way.

Abstract
Nowadays, human operators at control centers analyze a large volume of alarm information during outage events and must act fast to restore the service. To assist operator decisions this work proposes novel machine learning-based functions aiming to: (a) classify the complexity of a fault occurrence (Occurrences Classifier) and its cause (Fault Cause Classifier) based on its alarm events; (b) provide fast insights to the operator on how to solve it (Data2Actions). The Occurrences Classifier takes alarm information of an occurrence and classifies it as a simpleor complexoccurrence, while the Fault Cause Classifier predicts the cause class of MV lines faults. The Data2Actions takes a sequence of alarm information from the occurrence and suggests a more adequate sequence of switching actions to isolate the fault section. These algorithms were tested on real data from a Distribution System Operator and showed: (a) an accuracy of 86% for the Data2Actions, (b) an accuracy of 68% for the Occurrences Classifier, and (c) an accuracy of 74% for the Fault Cause Classifier. It also proposes a new representation for SCADA event log data using graphs, which can help human operators identify infrequent alarm events or create new features to improve model performance.