Datasets and Publications

With the vast amount of social media posts available online, topic modeling and sentiment analysis have become central methods to better understand and analyze online behavior and opinion. However, semantic and sentiment analysis have rarely been combined for joint topic-sentiment modeling which yields semantic topics associated with sentiments. Recent breakthroughs in natural language processing have also not been leveraged for joint topic-sentiment modeling so far. Inspired by these advancements, this paper presents a novel framework for joint topic-sentiment modeling of short texts based on pre-trained language models and a clustering approach. The method leverages techniques from dimensionality reduction and clustering for which multiple algorithms were considered. All configurations were experimentally compared against existing joint topic-sentiment models and an independent sequential baseline. Our framework produced clusters with semantic topic quality scores of up to 0.23 while the best score among the previous approaches was 0.12. The sentiment classification accuracy increased from 0.35 to 0.72 and the uniformity of sentiments within the clusters reached up to 0.9 in contrast to the baseline of 0.56. The presented approach can benefit various research areas such as disaster management where sentiments associated with topics can provide practical useful information.

Effective decision-making in natural disaster management relies heavily on a comprehensive understanding of the situation in affected areas. Social media has been established as a tool to monitor human response and damage assessment. Given the vast amounts of data available, computational methods such as topic modelling are typically employed to reduce information complexity. However, these methods mostly neglect aspects such as geographic location and emotional response, which frequently results in sequential workflows of initial semantic filtering and subsequent spatial or spatio-temporal analysis. This study presents a novel approach for multimodal information extraction from geo-social media data for aiding decision support in disaster management. The method leverages a spatial, temporal, semantic, and sentiment-based clustering approach of social media posts to extract clusters that provide insights into disaster-related content. A case study in the Ahr Valley region in Germany demonstrates the method’s effectiveness in providing actionable insights for disaster response and management. The approach offers a tool for the quick assessment of disaster-related information from social media, potentially aiding timely and informed decision-making.

© 2025 N. Militsis, V. Mygdalis, I. Pitas. This is the authors' version of the work. It is posted here for your personal use. Not for redistribution

The Multi-Head Self-Attention (MHSA) mechanism stands as the cornerstone of Transformer architectures, endowing them with unparalleled expressive capabilities. The main learnable parameters in a transformer self-attention block include matrices that project the input features into subspaces, where similarity metrics are thereby calculated. In this paper, we argue that we could use less learnable parameters for achieving good projections. We propose the Structured Efficient Self-Attention (SESA) module, a generic paradigm inspired by the Johnson-Lindenstrauss (JL) lemma, that employs an Adaptive Fast JL Transform (A-FJLT) parameterised by a single learnable vector for each projection. This allows us to eliminate a substantial 75% of the learnable parameters of the legacy MHSA, with very slight sacrifices to accuracy. SESA properties are showcased on the demanding task of object detection at the COCO dataset, achieving comparable performance with its computationally intensive counterparts.

Stereo matching has emerged as a cost-effective solution for road surface 3D reconstruction, garnering significant attention towards improving both computational efficiency and accuracy. This article introduces decisive disparity diffusion (D3Stereo), marking the first exploration of dense deep feature matching that adapts pre-trained deep convolutional neural networks (DCNNs) to previously unseen road scenarios. A pyramid of cost volumes is initially created using various levels of learned representations. Subsequently, a novel recursive bilateral filtering algorithm is employed to aggregate these costs. A key innovation of D3Stereo lies in its alternating decisive disparity diffusion strategy, wherein intra-scale diffusion is employed to complete sparse disparity images, while inter-scale inheritance provides valuable prior information for higher resolutions. Extensive experiments conducted on our created UDTIRI-Stereo and Stereo-Road datasets underscore the effectiveness of D3Stereo strategy in adapting pre-trained DCNNs and its superior performance compared to all other explicit programming-based algorithms designed specifically for road surface 3D reconstruction. Additional experiments conducted on the Middlebury dataset with backbone DCNNs pre-trained on the ImageNet database further validate the versatility of D3Stereo strategy in tackling general stereo matching problems.

General description of the dataset

The dataset will be used for the construction of a 3D model regarding the district of Agios Thomas in Larisa, Greece, after the flood events of 2023. It is comprised of 795 UAV video frames, taken from four publicly available videos.

Dataset Structure

Within the dataset, a dedicated folder contains four CSV files. Each file provides the link to the original video and specifies the video frames that were utilized from each source.

Details on acquiring the dataset can be found here.