Board of Directors' Profile: A Case for Deep Learning as a Valid Methodology to Finance Research

Vaca, César Gutiérrez; Tejerina, F.; Sahelices, Benjamin

doi:10.9781/ijimai.2022.09.005

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI models can be easily integrated into software systems, as dealing with changing requirements for data, feature modeling, monitoring, debugging, and updating models can be easily performed with MLOps. Studies in the literature present model architectures for solving problems [28][29][30], as well as explain how these models are integrated into software systems using MLOps.…”

Section: Natural Language Processing and Sentiment Analysismentioning

confidence: 99%

Deep learning-based user experience evaluation in distance learning

et al. 2023

View full text Add to dashboard Cite

The Covid-19 pandemic caused uncertainties in many different organizations, institutions gained experience in remote working and showed that high-quality distance education is a crucial component in higher education. The main concern in higher education is the impact of distance education on the quality of learning during such a pandemic. Although this type of education may be considered effective and beneficial at first glance, its effectiveness highly depends on a variety of factors such as the availability of online resources and individuals’ financial situations. In this study, the effectiveness of e-learning during the Covid-19 pandemic is evaluated using posted tweets, sentiment analysis, and topic modeling techniques. More than 160,000 tweets, addressing conditions related to the major change in the education system, were gathered from Twitter social network and deep learning-based sentiment analysis models and topic models based on latent dirichlet allocation (LDA) algorithm were developed and analyzed. Long short term memory-based sentiment analysis model using word2vec embedding was used to evaluate the opinions of Twitter users during distance education and also, a topic model using the LDA algorithm was built to identify the discussed topics in Twitter. The conducted experiments demonstrate the proposed model achieved an overall accuracy of 76%. Our findings also reveal that the Covid-19 pandemic has negative effects on individuals 54.5% of tweets were associated with negative emotions whereas this was relatively low on emotion reports in the YouGov survey and gender-rescaled emotion scores on Twitter. In parallel, we discuss the impact of the pandemic on education and how users’ emotions altered due to the catastrophic changes allied to the education system based on the proposed machine learning-based models.

show abstract

Section: Natural Language Processing and Sentiment Analysismentioning

confidence: 99%

Deep learning-based user experience evaluation in distance learning

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Specifically, to extract more accurate fog region features, we propose a fog region segmentation algorithm-ASRS to segment the fog region in the image, and then we perform feature statistics from the transmission matrix, dark channel matrix, and other feature information of the image, Then the obtained features are used as the "engineering features" for visibility estimation. Next, we introduce the Transformer, which was first used in the field of Natural Language Processing(NLP) to the field of visibility estimation to build a visibility estimation network [44]. Meanwhile, to extract more effective semantic information, we embed the CA attention mechanism into Transformer.…”

mentioning

confidence: 99%

FGS-Net: A Visibility Estimation Method Based on Statistical Feature Stream in Fog Area

Liu

Zhong

et al. 2023

Preprint

View full text Add to dashboard Cite

Low visibility always leads to serious traffic accidents worldwide, and it remains a tough problem despite the extensive work researched in the field of meteorology. Therefore, we propose a novel end-to-end network, FGS-Net, for visibility estimation, combining "engineered features" and "learned features" to achieve higher accuracy. Specifically, we propose a novel and effective fog region segmentation method, named ASRS(Auto Seed Region Segmentation), to segment the fog regions in the input image. Subsequently, two "specific features" (transmittance matrix, dark channel matrix) and three "common features" (contrast, average gradient, brightness) are extracted from the fog region. Next, the feature information of the fog region is statistically calculated as "engineering features" for visibility estimation. In addition, our approach uses Transformer, a classical model commonly used in the field of Natural Language Processing (NLP) to obtain the "learned features" for visibility estimation. Furthermore, in order to obtain more efficient "learned features", we embed the Coordinate Attention (CA) module in FGS-Net. Finally, to verify the effectiveness and superiority of our method, We evaluate our approach on two visibility datasets: Visibility Image Dataset Ⅰ (VID I) and Visibility Image Dataset Ⅱ (VID II), where VID I is a real scene visibility dataset and VID II is a synthetic visibility dataset. The experimental results show that our method has better performance than the classical one on these two datasets. And compared with the runner-up, it has 2.2% and 0.9% higher accuracy in VID I and VID II, respectively.

show abstract

Interpretability of deep learning models in analysis of Spanish financial text

Vaca,

Astorgano,

López-Rivero

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

Artificial intelligence methods based on deep learning (DL) have recently made significant progress in many different areas including free text classification and sentiment analysis. We believe that corporate governance is one of these areas, where DL can generate very valuable and differential knowledge, for example, by analyzing the biographies of independent directors, which allows for qualitative modeling of their profile in an automatic way. For this technology to be accepted it is important to be able to explain how it generates its results. In this work we have developed a six-dimensional labeled dataset of independent director biographies, implemented three recurrent DL models based on LSTM and transformers along with four ensembles, one of which is an innovative proposal based on a multi-layer perceptron (MLP), trained them using Spanish language and economics and finance terminology and performed a comprehensive test study that demonstrates the accuracy of the results. We have also performed a complete study of explainability using the SHAP methodology by comparatively analyzing the developed models. We have achieved a mean error (MAE) of 8% in the modeling of the open text biographies, which has allowed us to perform a case study of time analysis that has detected significant variations in the composition of the Standard Expertise Profile (SEP) of the boards of directors, related to the crisis of the period 2008–2013. This work shows that DL technology can be accurately applied to free text analysis in the finance and economic domain, by automatically analyzing large volumes of data to generate knowledge that would have been unattainable by other means.

show abstract

Board of Directors' Profile: A Case for Deep Learning as a Valid Methodology to Finance Research

Cited by 3 publications

References 0 publications

Deep learning-based user experience evaluation in distance learning

Deep learning-based user experience evaluation in distance learning

FGS-Net: A Visibility Estimation Method Based on Statistical Feature Stream in Fog Area

Interpretability of deep learning models in analysis of Spanish financial text

Contact Info

Product

Resources

About