13 November 2021 in The VLDB Journal
25 August 2021 in IEEE Access
Social media plays a significant role in disaster management by providing valuable data about affected people, donations, and help requests. Recent studies highlight the need to filter information on social media into fine-grained content labels. However, identifying useful information from massive amounts of social media posts during a crisis is a challenging task. In this paper, we propose I-AID, a multimodel approach to automatically categorize tweets into multi-label information types and filter critical information from the enormous volume of social media data. I-AID incorporates three main components: i) a BERT-based encoder to capture the semantics of a tweet and represent as a low-dimensional vector, ii) a graph attention network (GAT) to apprehend correlations between tweets’ words/entities and the corresponding information types, and iii) a Relation Network as a learnable distance metric to compute the similarity between tweets and their corresponding information types in a supervised way. We conducted several experiments on two real publicly-available datasets. Our results indicate that I-AID outperforms state-of-the-art approaches in terms of weighted average F1 score by +6% and +4% on the TREC-IS dataset and COVID-19 Tweets, respectively.
13 September 2019 in Data Science
An increasing number of solutions aim to support the steady increase of the number of requirements and requests for Linked Data at scale. This plethora of solutions leads to a growing need for objective means that facilitate the selection of adequate solutions for particular use cases. We hence present Hobbit, a distributed benchmarking platform designed for the unified execution of benchmarks for Linked Data solutions. The Hobbit benchmarking platform is based on the FAIR principles and is the first benchmarking platform able to scale up to benchmarking real-world scenarios for Big Linked Data solutions. Our online instance of the platform has more than 300 registered users and offers more than 40 benchmarks. It has been used in eleven benchmarking challenges and for more than 13000 experiments. We give an overview of the results achieved during 2 of these challenges and point to some of the novel insights that were gained from the results of the platform. Hobbit is open-source and available at http://github.com/hobbit-project .