The NorthCap University

Investors' opinions and attitudes toward an investment have become increasingly important in today's world. The increasing amount of platforms (such as Twitter) for sharing information has enabled people's sentiments (how they feel about something) to be leveraged as quantifiable data for academic analysis. The study conducted quantifiable methodology to ascertain whether or not sentiment as a standalone variable would be an appropriate metric to predict the direction of stock prices. The traditional method of using regression analysis to create predictive models was replaced with a binary-classification format where the sentiment around the company was combined with the previous day's closing price to produce a model predicting whether the stock would rise or fall. Tweets were collected about numerous companies and subjected to comprehensive NLP analysis (including tokenization, lemmatization, and removing stopwords) before being summed with the VADER model, creating a continually changing visual representation of investor sentiment. Once the models were developed, traditional machine-learning techniques and deep-learning architectures were utilized to compare performance. Overall the results showed significant improvements in predicting price movement direction by including investor sentiment as a metric in the pricing model compared with models based solely on historical data. The enhanced performance, particularly observed in temporal models like BiLSTM+Attention, provides robust evidence that human emotion, quantified through collective social discourse, significantly improves accuracy and flexibility in data-driven stock market prediction systems. This study validates the integration of behavioral insights as a critical, non-technical source of alpha in quantitative finance.

Abstract Sustainable citizenship has emerged as a critical yet enigmatic concept in the pursuit of achieving sustainable societies. Despite considerable scholarly attention, the intricate connections between sustainable citizenship and societal sustainability remain underexplored. This study seeks to bridge this gap by conducting a comprehensive systematic literature review and bibliometric analysis of 379 research articles. Using VOSviewer and the Biblioshiny package within R Studio, we unveil publication trends and identify the most influential sources, offering valuable insights for both established and nascent researchers. Furthermore, themes are discussed using science mapping which uncovers underexplored and emergent themes, shedding light on promising directions for future inquiry. By synthesizing existing knowledge and proposing a forward-looking research agenda, this study contributes to a deeper understanding of how sustainable citizenship can serve as a cornerstone for fostering sustainable societies. The themes exploring the conjunction of sustainable citizenship and society and a framework developed express varied angles via which such societies may be developed.

Abstract This paper investigates the enhancement of communication performance in mixed radio frequency–free space optical (RF–FSO) wireless networks by employing unmanned aerial vehicles (UAVs) as mobile relays. A dual-hop transmission model is considered, where the UAV acts as an intermediary between a fixed ground source and multiple mobile users distributed along the boundary of a predefined geographical region. To improve the reliability and efficiency of the system, we propose a joint optimization framework that determines the UAV’s optimal altitude and horizontal location. Additionally, an opportunistic user scheduling mechanism is implemented, selecting the mobile user with the highest instantaneous signal-to-noise ratio (SNR) for communication. The RF link is modeled using Rayleigh fading statistics, and the FSO link is modeled using the Gamma–Gamma fading distribution, capturing the effects of atmospheric turbulence, pointing errors, and angle-of-arrival fluctuations. Closed-form expressions for outage probability and its asymptotic approximation at high SNR levels are derived to evaluate system performance analytically. The analytical results are further validated through Monte Carlo simulations. The outcomes demonstrate that the proposed UAV positioning strategy and user scheduling scheme effectively minimize outage probability and significantly enhance the robustness of the RF–FSO communication system. These results provide valuable insights for the deployment of UAV-assisted hybrid optical wireless networks in dynamic or infrastructure-constrained environments.

Social networks are increasingly in demand for text mining applications. Text analysis has become a more popular technique used on the internet. Social media platforms provide abundant access to text data, allowing users to post comments, making the analysis of these comments crucial for various business applications. Sentiment analysis (SA) is a subfield of natural language processing that aims to automatically identify and classify opinions expressed in text as positive, negative, or neutral. It plays a crucial role in understanding public opinion, especially when applied to large-scale textual data from social media platforms. However, social media data extraction policies governed by platform-specific APIs, privacy constraints, and data usage limitations pose challenges in acquiring high-quality, representative datasets for research. This study proposes TSAPM-BERT, a parametrically modified BERT-based framework that integrates a weighted attention mechanism, information from the sentiment lexicon and optimization of the learning rate to enhance the classification of sentiment at the aspect level. We evaluate the model on a benchmark emotion dataset, comparing its performance against traditional machine learning and deep learning baselines. Experimental results demonstrate that TSAPM-BERT achieves a training accuracy of 99.37 and testing accuracy of 98.52, outperforming competing methods. This work provides a reproducible framework that bridges the gap between high-accuracy sentiment classification and the practical constraints of social media data usage.

Detecting hate speech is a significant task in understanding the contents published online, particularly in natural language processing. Strong automated systems that can identify and minimize harmful online communication are therefore becoming necessary. The aim of this study is to compare classical deep learning models against transformer-based architectures to find a technique for identifying hate speech written in English. Using a hate speech classification labeled dataset, the study determine the performance of each model across evaluation metrics like accuracy, precision, recall and F1-score. For addressing class imbalance and improve generalization, methods like focal loss and data augmentation were applied. Our findings indicate that the models based on transformers, particularly RoBERTa-large, significantly outperform traditional architectures in finding out subtle and context-dependent instances of hate speech. This research highlights emerging importance of large pre-trained language models and hybrid ways for enhancing automated hate speech detection systems.

This article examines the impact of spillovers from unconventional and conventional monetary policies during and after the COVID-19 pandemic. The study analyses eight countries—five advanced economies (Australia, Canada, New Zealand, the United Kingdom, and the United States) and three emerging economies (Brazil, India, and South Africa), to assess monetary policy spillovers across eight sectors from 2019 to 2025, using the event study methodology. The results indicate that emerging markets experienced greater sectoral monetary policy spillovers than advanced economies. In the case of conventional monetary policy spillovers, both advanced and emerging markets responded similarly. Monetary policy is one of the most effective policies for guiding sectoral dynamics. The results of this study may help investors and policymakers. JEL Codes : E4, E44, E5