Combining bag-of-words and sentiment features of annual reports to predict abnormal stock returns

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F18%3A39913373" target="_blank" >RIV/00216275:25410/18:39913373 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s00521-017-3194-2" target="_blank" >https://link.springer.com/article/10.1007/s00521-017-3194-2</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00521-017-3194-2" target="_blank" >10.1007/s00521-017-3194-2</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Combining bag-of-words and sentiment features of annual reports to predict abnormal stock returns

Popis výsledku v původním jazyce

Automated textual analysis of firm-related documents has become an important decision support tool for stock market investors. Previous studies tended to adopt either dictionary-based or machine learning approach. Nevertheless, little is known about their concurrent use. Here we use the combination of financial indicators, readability, sentiment categories, and bag-of-words (BoW) to increase prediction accuracy. This paper aims to extract both sentiment and BoW information from the annual reports of US firms. The sentiment analysis is based on two commonly used dictionaries, namely a general dictionary Diction 7.0 and a finance-specific dictionary proposed by Loughran and McDonald (J Finance 66:35-65, 2011. doi:10.1111/j.1540-6261.2010.01625.x). The BoW are selected according to their tf-idf. We combine these features with financial indicators to predict abnormal stock returns using a multilayer perceptron neural network with dropout regularization and rectified linear units. We show that this method performs similarly as na Naive Bayes and outperforms other machine learning algorithms (support vector machine, C4.5 decision tree, and k-nearest neighbour classifier) in predicting positive/negative abnormal stock returns in terms of ROC. We also show that the quality of the prediction significantly increased when using the correlation-based feature selection of BoW. This prediction performance is robust to industry categorization and event window.

Název v anglickém jazyce

Combining bag-of-words and sentiment features of annual reports to predict abnormal stock returns

Popis výsledku anglicky

Automated textual analysis of firm-related documents has become an important decision support tool for stock market investors. Previous studies tended to adopt either dictionary-based or machine learning approach. Nevertheless, little is known about their concurrent use. Here we use the combination of financial indicators, readability, sentiment categories, and bag-of-words (BoW) to increase prediction accuracy. This paper aims to extract both sentiment and BoW information from the annual reports of US firms. The sentiment analysis is based on two commonly used dictionaries, namely a general dictionary Diction 7.0 and a finance-specific dictionary proposed by Loughran and McDonald (J Finance 66:35-65, 2011. doi:10.1111/j.1540-6261.2010.01625.x). The BoW are selected according to their tf-idf. We combine these features with financial indicators to predict abnormal stock returns using a multilayer perceptron neural network with dropout regularization and rectified linear units. We show that this method performs similarly as na Naive Bayes and outperforms other machine learning algorithms (support vector machine, C4.5 decision tree, and k-nearest neighbour classifier) in predicting positive/negative abnormal stock returns in terms of ROC. We also show that the quality of the prediction significantly increased when using the correlation-based feature selection of BoW. This prediction performance is robust to industry categorization and event window.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA16-19590S" target="_blank" >GA16-19590S: Analýza témat a sentimentu vícenásobných textových zdrojů pro finanční rozhodování podniků</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neural Computing and Applications

ISSN

0941-0643

e-ISSN

—

Svazek periodika

29

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

343-358

Kód UT WoS článku

000427799400005

EID výsledku v databázi Scopus

2-s2.0-85028574890