The Covid-19 pandemic made a significant impact on society, including the widespread implementation of lockdowns to prevent the spread of the virus. This measure led to a decrease in face-to-face social interactions and, as an equivalent, an increase in the use of social media platforms, such as Twitter. As part of Industry 4.0, sentiment analysis can be exploited to study public attitudes toward future pandemics and sociopolitical situations in general. This work presents an analysis framework by applying a combination of natural language processing techniques and machine learning algorithms to classify the sentiment of each tweet as positive, or negative. Through extensive experimentation, we expose the ideal model for this task and, subsequently, utilize sentiment predictions to perform time series analysis over the course of the pandemic. In addition, a change point detection algorithm was applied in order to identify the turning points in public attitudes toward the pandemic, which were validated by cross-referencing the news report at that particular period of time. Finally, we study the relationship between sentiment trends on social media and, news coverage of the pandemic, providing insights into the public’s perception of the pandemic and its influence on the news.

Nowadays, biomedical data are generated exponentially, creating datasets for analysis with ultra-high dimensionality and complexity. An indicative example is emerging single-cell RNA-sequencing (scRNA-seq) technology, which isolates and measures individual cells. The analysis of scRNA-seq data consists of a major challenge because of its ultra-high dimensionality and complexity. Towards this direction, we study the generalization of the MRPV, a recently published ensemble classification algorithm, which combines multiple ultra-low dimensional random projected spaces with a voting scheme, while exposing its ability to enhance the performance of base classifiers. We empirically showed that we can design a reliable ensemble classification technique using random projected subspaces in an extremely small fixed number of dimensions, without following the restrictions of the classical random projection method. Therefore, the MPRV acquires the ability to efficiently and rapidly perform classification tasks even for data with extremely high dimensionality. Furthermore, through the experimental analysis in six scRNA-seq data, we provided evidence that the most critical advantage of MRPV is the dramatic reduction in data dimensionality that allows for the utilization of computational demanding classifiers that are considered as non-practical in real-life applications. The scalability, the simplicity, and the capabilities of our proposed framework render it as a tool-guide for single-cell RNA-seq data which are characterized by ultra-high dimensionality. MRPV is available on GitHub in MATLAB implementation.

The utilization of large language models (LLMs) in research is becoming increasingly prevalent, as they offer advanced capabilities in processing and generating human-like text. However, this advancement comes with a significant trade-off in terms of time and computational costs. In this paper, we demonstrate that analyzing large text datasets with the use of LLMs can be performed efficiently in terms of both time and energy. For this purpose, we utilize the Llama pre-trained model. In more detail, we study the topic modeling task where the goal is to discover and identify topics in large text corpora. The basis of our approach is a hierarchical divisive clustering technique that clusters the data based on their semantic similarity, after employing a Sentence-BERT encoder, pre-trained on a variety of data across different tasks. Then, using an LLM, we identify topics for representative samples from each cluster. Additionally, we introduce a new evaluation method that leverages the capabilities of LLMs to assess the alignment between discovered topics and ground truth labels, providing a robust validation metric. Our findings indicate that it is possible to effectively reduce the computational cost of the topic modeling process compared to the direct application of LLMs and BERTopic, while simultaneously enhancing inference time and overall efficiency, thereby surpassing the current state-of-the-art capabilities of BERTopic.