Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment

碩士 === 國立成功大學 === 會計學系 === 107 === In recent years, the development of machine learning and deep learning have been remarkably advanced due to the rapid growth of computer hardware. In addition, many studies have shown that deep learning techniques have achieved good results in the theme of Natural...

Full description

Bibliographic Details
Main Authors: Zhe-WeiXu, 許哲維
Other Authors: Meng-Feng Yen
Format: Others
Language:zh-TW
Published: 2019
Online Access:http://ndltd.ncl.edu.tw/handle/3etw3m
id ndltd-TW-107NCKU5385006
record_format oai_dc
spelling ndltd-TW-107NCKU53850062019-10-26T06:24:11Z http://ndltd.ncl.edu.tw/handle/3etw3m Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment 應用深度學習分析經理人情緒並預測公司過度投資 Zhe-WeiXu 許哲維 碩士 國立成功大學 會計學系 107 In recent years, the development of machine learning and deep learning have been remarkably advanced due to the rapid growth of computer hardware. In addition, many studies have shown that deep learning techniques have achieved good results in the theme of Natural Language Processing. In this study, we apply the deep learning-based textual analysis to convert texts into sentiment scores, which are then used measure CEO's sentiment to predict over-investment. By doing so, we can not only quantify texts into meaningful numbers but also make decision based on the analyzed results. We found that the sentiment scores are positively related to over-investment. Negative sentiment tends to have a greater impact on over-investment than positive sentiment. Finally, when multiplied by arousal, valence would show more explanatory power. Meng-Feng Yen 顏盟峯 2019 學位論文 ; thesis 38 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 會計學系 === 107 === In recent years, the development of machine learning and deep learning have been remarkably advanced due to the rapid growth of computer hardware. In addition, many studies have shown that deep learning techniques have achieved good results in the theme of Natural Language Processing. In this study, we apply the deep learning-based textual analysis to convert texts into sentiment scores, which are then used measure CEO's sentiment to predict over-investment. By doing so, we can not only quantify texts into meaningful numbers but also make decision based on the analyzed results. We found that the sentiment scores are positively related to over-investment. Negative sentiment tends to have a greater impact on over-investment than positive sentiment. Finally, when multiplied by arousal, valence would show more explanatory power.
author2 Meng-Feng Yen
author_facet Meng-Feng Yen
Zhe-WeiXu
許哲維
author Zhe-WeiXu
許哲維
spellingShingle Zhe-WeiXu
許哲維
Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
author_sort Zhe-WeiXu
title Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
title_short Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
title_full Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
title_fullStr Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
title_full_unstemmed Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
title_sort apply deep learning to analyze ceo’s sentiment and predict firms’ overinvestment
publishDate 2019
url http://ndltd.ncl.edu.tw/handle/3etw3m
work_keys_str_mv AT zheweixu applydeeplearningtoanalyzeceossentimentandpredictfirmsoverinvestment
AT xǔzhéwéi applydeeplearningtoanalyzeceossentimentandpredictfirmsoverinvestment
AT zheweixu yīngyòngshēndùxuéxífēnxījīnglǐrénqíngxùbìngyùcègōngsīguòdùtóuzī
AT xǔzhéwéi yīngyòngshēndùxuéxífēnxījīnglǐrénqíngxùbìngyùcègōngsīguòdùtóuzī
_version_ 1719278504901607424