Search Results (3)

Effectively harnessing the power of social media data for disaster management requires sophisticated analysis methods and frameworks. This research focuses on understanding the contextual information present in social media posts during disasters and developing a taxonomy to effectively categorize and classify the diverse range of topics discussed. First, the existing literature on social media analysis in disaster management is explored, highlighting the limitations and gaps in current methodologies. Second, a dataset comprising real-time social media posts related to various disasters is collected and preprocessed to ensure data quality and reliability. Third, three well-established topic modeling techniques, namely Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and Non-Negative Matrix Factorization (NMF), are employed to extract and analyze the latent topics and themes present in the social media data. The contributions of this research lie in the development of a taxonomy that effectively categorizes and classifies disaster-related social media data, the identification of key latent topics and themes, and the extraction of valuable insights to support and enhance emergency management efforts. Overall, the findings of this research have the potential to transform the way emergency management and response are conducted by harnessing the power of social media data. By incorporating these insights into decision-making processes, emergency managers can make more informed and strategic choices, resulting in more efficient and effective emergency response strategies. This, in turn, leads to improved outcomes, better utilization of resources, and ultimately, the ability to save lives and mitigate the impacts of disasters. Full article

This article presents a dataset of 10,917 news articles with hierarchical news categories collected between 1 January 2019 and 31 December 2019. We manually labeled the articles based on a hierarchical taxonomy with 17 first-level and 109 second-level categories. This dataset can be used to train machine learning models for automatically classifying news articles by topic. This dataset can be helpful for researchers working on news structuring, classification, and predicting future events based on released news. Full article

In the digital multimedia era, digital forensics is becoming an emerging area of research thanks to the large amount of image and video files generated. Ensuring the integrity of such media is of great importance in many situations. This task has become more complex, especially with the progress of symmetrical and asymmetrical network structures which make their authenticity difficult. Consequently, it is absolutely imperative to discover all possible modes of manipulation through the development of new forensics detector tools. Although many solutions have been developed, tamper-detection performance is far from reliable and it leaves this problem widely open for further investigation. In particular, many types of multimedia fraud are difficult to detect because some evidences are not exploited. For example, the symmetry and asymmetry inconsistencies related to visual feature properties are potential when applied at multiple scales and locations. We explore here this topic and propose an understandable soft taxonomy and a deep overview of the latest research concerning multimedia forgery detection. Then, an in-depth discussion and future directions for further investigation are provided. This work offers an opportunity for researchers to understand the current active field and to help them develop and evaluate their own image/video forensics approaches. Full article