Impact of Sentiment analysis on Energy Sector Stock Prices: A FinBERT Approach

Ben Yahia Sarra, Garcia Sanchez Jose Angel and Hentati Kaffel  Rania, (2024), Impact of Sentiment analysis on Energy Sector Stock Prices: A FinBERT Approach, Working Papers, HAL, https://EconPapers.repec.org/RePEc:hal:wpaper:hal-04629569.
 

Working Papers from HAL

Abstract: This study provides sentiment analysis model to enhance market return forecasts by considering investor sentiment from social media platforms like Twitter (X). We leverage advanced NLP techniques and large language models to analyze sentiment from financial tweets. We use a large web-scrapped data of selected energy stock daily returns spanning from 2018 to 2023. Sentiment scores derived from FinBERT are integrated into a novel predictive model (SIMDM) to evaluate autocorrelation structures within both the sentiment scores and stock returns data. Our findings reveal i) significant correlations between sentiment scores and stock prices. ii) Results are highly sensitive to data quality. iii) Our study reinforces the concept of market efficiency and offers empirical evidence regarding the delayed influence of emotional states on stock returns.

Keywords: financial NLP finBERT information extraction webscraping sentiment analysis; financial NLP; finBERT; information extraction; webscraping; sentiment analysis; LLM; Deep learing (search for similar items in EconPapers)

In this paper, we compare the performance of two non-parametric methods of classification and regression trees (CART) and the newly multivariate adaptive regression splines (MARS) models, in forecasting bankruptcy. Models are tested on a large universe of US banks over a complete market cycle and run under a K-fold cross validation. Then, a hybrid model which combines K-means clustering and MARS is tested as well. Our findings highlight that (i) Either in training or testing sample, MARS provides, in average, better correct classification rate than CART model (ii) Hybrid approach significantly increases the classification accuracy rate in the training sample (iii) MARS prediction underperforms when the misclassification of the bankrupt banks rate is adopted as a criteria (iv) Finally, results prove that non-parametric models are more suitable for bank failure prediction than the corresponding Logit model. 

In this paper, we use random subspace method to compare the classification and prediction of both canonical discriminant analysis and logistic regression models with and without misclassification costs. They have been applied to a large panel of US banks over the period 2008–2013. Results show that model’s accuracy have improved in case of more appropriate cut-off value C*ROC that maximizes the overall correct classification rate under the ROC curve. We also have tested the newly H-measure of classification performance and provided results for different parameters of misclassification costs. Our main conclusions are: (1) The logit model outperforms the CDA one in terms of correct classification rate by using usual cut-off parameters, (2) C*ROC improves the accuracy of classification in both CDA and logit regression, (3) H-measure and ROC curve validation improve the quality of the model by minimizing the error of misclassification of bankrupt banks. Moreover, it emphasizes better prediction of banks failure because it delivers in average the highest error type II. 

We examine the maximization problem of performance measure of financial structured products. For this purpose, we introduce the kappa ratios, based on downside risk measures which take account of the asymmetry of the return probability distribution. First, we deal with the optimization of some standard structured portfolios. We examine in particular the optimal combination of risk free, stock and call/put instruments with respect to kappa performance measures and in particular to the Sharpe–Omega ratio. Then, we provide the general solution of the optimal positioning problem with respect to kappa ratios. We analyze its properties and compare it to the portfolio profile that is optimal with respect to the standard expected utility criterion. 

In this paper, we study and extend the optimal portfolio positioning problem introduced by Brennan and Solanki (1981) and by Leland (1980). For that purpose, we introduce mixtures of probability distributions to model the log returns of financial assets. In this framework, we provide and analyze the general solution for log return with mixture distributions, in particular for the mixture Gaussian case. Our solution is characterized for arbitrary utility functions and for any risk neutral probability. Moreover, we illustrate the solution for a CRRA utility and for the minimal risk-neutral probability. Lastly, we compare our solution with the optimal portfolio within ambiguity. Our results have significant implications to improve the management of structured financial portfolios. 

In this paper, we use nonparametric runs-based tests to analyze the randomness and the persistence of relative returns of hedge funds. Runs tests are implemented on a universe of hedge funds extracted from HFR database over the period spanning January 2000 to December 2012. Our findings suggest that i) slightly less than 80% of the studied universe has returns at random, ii) a similar figure is found out when focusing on relative returns, iii) hedge funds that do present clustering in their relative returns are mainly found within Event Driven and Relative Value strategies, iv) and for relative returns, results vary with the type of the benchmark nature (peer group average or traditional). This paper also emphasizes that runs tests may be a useful tool for investors in their fund's selection process. 

The major contribution of this paper is to make use of generalized runs tests (Cho and White, 2011) to analyze the randomness, i.e. the lack of persistence, in both absolute and relative returns of hedge funds. We find that about 42% of the HFR universe exhibit iid absolute returns over the period spanning 2000 to 2012. These funds are mainly found in proportions within the Macro and Equity Hedge strategies. A similar result holds for relative returns. We also find that funds having non-iid returns often exhibit ARCH effects and structural breaks, with largest breaks located within financial crises. Also, only a small percentage displays persistence in their relative performance, 8.2% to 16.7% of the universe, mainly found in proportions within the Relative Value and Event-Driven strategies. The robustness of results is challenged by implementing the tests on a crisis-free period. We find similar results for absolute returns. For relative ones, differences appear across strategies and benchmarks, but still both ARCH and breaks are present. Our work contributes to the hedge fund literature in terms of methodology, portfolio allocation, and performance measurement. 

This paper provides accurate estimations of portfolio returns including several hedge funds. The main problem is to identify their dependence structure. For this purpose, we introduce goodness-of-fit tests of copula, based on the Kendall's functions. To illustrate our approach, we consider in particular different optimal portfolios, corresponding to the maximization of performance measures such as the Sharpe, Return on VaR, Return on CVaR and Omega ratios. The empirical validation is made on three hedge fund indices: the Event Driven, Long/Short and Managed Futures. The time period of the analysis is December 1993 to October 2008. Our results show that copula clearly allows a better determination of risk and performance measures of such portfolios. 

We introduce mixtures of probability distributions to model empirical distributions of financial asset returns. In this framework, we examine the problem of maximizing performance measures. For this purpose, we consider a large class of reward/risk ratios such as the Kappa measures and in particular the Omega ratio. This latter measure is associated to a downside risk measure based on a put component. All these measures can take account of the asymmetry of the probability distribution, which is important when dealing with mixture of distributions. We examine first a fundamental example: the ranking and maximization of Gaussian mixture distributions, according to the Omega performance measure. Then we provide a general result for the maximization of mixture distributions with respect to a very large family of performance measures, including Kappa measures.

Keywords: mixture of probability distributions; performance measures; Kappa measures; Omega ratio