Topic: Firm-Specific News Sentiment and Short-Horizon Risk-Adjusted Return Predictability: Evidence from Large Language Models

Description: Investigating whether firm-specific narrative sentiment embedded in financial news contains economically meaningful information for predicting short-horizon stock returns. The research develops a novel firm-level sentiment analysis framework that aligns textual sentiment with the economic unit of analysis—the individual firm. To support this objective, two expert-annotated Bloomberg-based datasets of financial news headlines and full-length articles were constructed using comprehensive annotation guidelines and validated through high inter-annotator agreement. These datasets are used to benchmark lexicon-based approaches, discriminative transformer models, and state-of-the-art generative Large Language Models (LLMs) under zero-shot and few-shot prompting strategies for target-level financial sentiment analysis. The extracted sentiment signals are subsequently integrated with technical indicators and historical market data to develop machine learning models for short-horizon stock return prediction. Finally, the economic value of LLM-derived firm-specific sentiment is evaluated through out-of-sample forecasting, trading strategy performance, Sharpe ratios, and Fama-French five-factor risk-adjusted alpha, demonstrating how advances in generative AI can improve sentiment measurement and contribute to behavioural asset pricing and quantitative finance. 

Topic: Analysis of Factors Influencing Willingness to Pay for Renewable Energy: The Case of Turkey

Description: Investigating the socioeconomic and behavioral determinants of households' willingness to pay for renewable energy in Turkey. The research employed the contingent valuation method to design and administer a large-scale survey of 2,500 households across 12 major metropolitan cities, collecting data on income, education, age, environmental awareness, and renewable energy preferences. Statistical and econometric analyses were conducted to identify the key factors influencing public support for green electricity and the willingness to finance renewable energy expansion. The findings provide evidence-based policy recommendations for promoting renewable energy adoption, supporting sustainable energy transition, and reducing dependence on conventional energy sources in developing economies.