本文關(guān)鍵詞：Web信息驅(qū)動(dòng)的上市公司財(cái)務(wù)危機(jī)預(yù)警研究　出處：《江西財(cái)經(jīng)大學(xué)》2013年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： Web金融信息 財(cái)務(wù)危機(jī) 情感傾向分析 動(dòng)態(tài)預(yù)警 靜態(tài)預(yù)警

【摘要】：市場(chǎng)經(jīng)濟(jì)的發(fā)展,使得公司間的競(jìng)爭(zhēng)日益激烈,而全球經(jīng)濟(jì)一體化,帶來的不僅僅是發(fā)展機(jī)遇,也暗藏了無盡的危機(jī)和風(fēng)險(xiǎn)。對(duì)上市公司而言,因?yàn)榘l(fā)生財(cái)務(wù)危機(jī)而被特別處理甚至被迫退市,不僅影響其自身的生存和發(fā)展,還會(huì)給投資者和債權(quán)人帶來巨大的經(jīng)濟(jì)損失。因此,對(duì)上市公司財(cái)務(wù)危機(jī)準(zhǔn)確、及時(shí)、有效地預(yù)警,無疑對(duì)促進(jìn)資本市場(chǎng)和國(guó)民經(jīng)濟(jì)的發(fā)展,維持社會(huì)穩(wěn)定具有重要作用。 財(cái)務(wù)危機(jī)預(yù)警研究主要涉及兩個(gè)方面：預(yù)警指標(biāo)和預(yù)警模型。已有的研究在預(yù)警指標(biāo)方面主要是選用財(cái)務(wù)指標(biāo),然而由于財(cái)務(wù)指標(biāo)的滯后性和易被操縱等固有缺陷,也有學(xué)者積極引入如宏觀經(jīng)濟(jì)變量、公司治理變量、產(chǎn)業(yè)變量等非財(cái)務(wù)指標(biāo),但是由于非財(cái)務(wù)指標(biāo)類型眾多,數(shù)據(jù)不易獲取,而且有些指標(biāo)難以量化,這些都為在財(cái)務(wù)危機(jī)預(yù)警中非財(cái)務(wù)指標(biāo)的引入造成障礙。而由于網(wǎng)絡(luò)技術(shù)的發(fā)展,Web金融信息大量涌現(xiàn),其所具有的實(shí)時(shí)性、覆蓋性、全面性和易獲取等特點(diǎn),正好彌補(bǔ)了非財(cái)務(wù)指標(biāo)獲取困難以及不完整、不全面等不足,為財(cái)務(wù)危機(jī)預(yù)警中非財(cái)務(wù)指標(biāo)的獲取提供了新的途徑。 對(duì)財(cái)務(wù)危機(jī)預(yù)警模型的研究,已有的研究成果從傳統(tǒng)的統(tǒng)計(jì)模型到人工智能模型,大多是用截面數(shù)據(jù)所建立的靜態(tài)預(yù)警模型,而上市公司的財(cái)務(wù)危機(jī)并不是突然發(fā)生,有一個(gè)逐漸演化的過程,靜態(tài)預(yù)警模型沒有考慮到預(yù)警指標(biāo)的時(shí)序特征,忽略了歷史數(shù)據(jù)對(duì)預(yù)警結(jié)果的影響,從而造成預(yù)警模型的早期預(yù)警效果較差,在實(shí)際應(yīng)用中難以推廣。 本文從以上兩個(gè)方面入手,一方面,研究如何將Web金融信息引入上市公司財(cái)務(wù)危機(jī)預(yù)警指標(biāo)體系以及Web金融信息指標(biāo)的預(yù)警作用；另一方面,研究上市公司財(cái)務(wù)危機(jī)的動(dòng)態(tài)預(yù)警。圍繞這兩大方面,本文具體研究了以下內(nèi)容： (1)研究了Web金融信息的量化問題。因?yàn)閃eb金融信息基本上是非結(jié)構(gòu)化的文本信息,所以,要將它納入到財(cái)務(wù)危機(jī)預(yù)警指標(biāo)體系,需要將它進(jìn)行合理地量化,文本內(nèi)容的情感傾向值計(jì)算是文本信息量化的常用手段。本文針對(duì)Web金融信息文本,構(gòu)建了金融領(lǐng)域情感詞典,提出了基于語素分?jǐn)?shù)的情感傾向值計(jì)算方法。 (2)分析了Web金融信息和上市公司財(cái)務(wù)狀況的關(guān)系。針對(duì)Web金融信息和上市公司財(cái)務(wù)狀況的關(guān)系,本文主要研究了兩個(gè)方面。首先,通過相關(guān)性分析研究了Web金融信息指標(biāo)(即信息熱度和情感值)與財(cái)務(wù)指標(biāo)的關(guān)系；其次,運(yùn)用Logistic回歸分析研究了Web金融信息指標(biāo)對(duì)預(yù)警上市公司是否會(huì)被ST的影響。 (3)驗(yàn)證了Web金融信息指標(biāo)對(duì)財(cái)務(wù)危機(jī)預(yù)警模型的影響。本文運(yùn)用LIBSVM分別構(gòu)建了純財(cái)務(wù)指標(biāo)預(yù)警模型和財(cái)務(wù)指標(biāo)與Web金融信息指標(biāo)相結(jié)合的混合模型,通過實(shí)證比較分析,發(fā)現(xiàn)加入Web金融信息指標(biāo)后,預(yù)警模型在超前性、穩(wěn)定性和有效性等方面都有很大程度的改善。 (4)研究了上市公司財(cái)務(wù)危機(jī)的動(dòng)態(tài)預(yù)警。本文首先運(yùn)用計(jì)量經(jīng)濟(jì)學(xué)的ARMA模型,對(duì)上市公司財(cái)務(wù)狀況的時(shí)序特征進(jìn)行擬合；然后借用質(zhì)量管理學(xué)上的控制圖思想,將Web金融信息情感褒貶程度指標(biāo)加入EWMA,構(gòu)建了上市公司財(cái)務(wù)危機(jī)動(dòng)態(tài)預(yù)警模型S-EWMA;最后對(duì)其進(jìn)行實(shí)證分析,與EWMA進(jìn)行了對(duì)比分析。 本文的創(chuàng)新性工作體現(xiàn)在： (1)提出了基于語素分?jǐn)?shù)的Web金融信息文本情感傾向值計(jì)算方法。目前,文本情感傾向性計(jì)算方面已有不少的研究成果,但是計(jì)算方法往往受到種子詞選擇和情感詞典覆蓋性等方面的限制,而且專門關(guān)于金融領(lǐng)域文本情感計(jì)算的研究尚未發(fā)現(xiàn)。本文所提出的基于語素分?jǐn)?shù)的Web金融信息文本情感傾向值計(jì)算方法,具有領(lǐng)域針對(duì)性,能充分滿足金融領(lǐng)域文本情感傾向性分析的要求。首先,構(gòu)建了金融領(lǐng)域的情感詞典,將金融領(lǐng)域的特色情感詞添加到詞典中,而基于語素分?jǐn)?shù)的情感值計(jì)算方法很好地解決了情感詞典的覆蓋性問題；其次,在進(jìn)行句子和文檔的情感傾向值計(jì)算時(shí),充分考慮文檔結(jié)構(gòu)中的否定詞和程度副詞對(duì)文檔情感傾向所起的修飾作用,考慮了句子在文檔不同位置對(duì)情感傾向的貢獻(xiàn)不同,從而被賦予不同權(quán)重,以及子句間連接詞的轉(zhuǎn)折、遞進(jìn)、并列等模式對(duì)句子情感傾向的影響,而不是將各組成部分的情感值進(jìn)行簡(jiǎn)單地求和。實(shí)驗(yàn)結(jié)果也驗(yàn)證了本文計(jì)算方法的有效性。 (2)分析了Web金融信息和上市公司財(cái)務(wù)狀況的相關(guān)性。本文通過對(duì)Web金融信息和上市公司財(cái)務(wù)狀況的關(guān)系分析,發(fā)現(xiàn)Web金融信息文本情感值中含有財(cái)務(wù)指標(biāo)未曾包含的與上市公司財(cái)務(wù)狀況相關(guān)的信息,因此Web金融信息情感值可以作為上市公司財(cái)務(wù)指標(biāo)的重要補(bǔ)充。 (3)構(gòu)建了財(cái)務(wù)指標(biāo)與Web金融信息指標(biāo)相結(jié)合的上市公司財(cái)務(wù)危機(jī)預(yù)警模型。本文結(jié)合Web金融信息指標(biāo)和財(cái)務(wù)指標(biāo)構(gòu)建了混合指標(biāo)的上市公司財(cái)務(wù)危機(jī)預(yù)警模型,實(shí)證結(jié)果表明,該模型在預(yù)警的有效性、穩(wěn)定性和超前性等方面均優(yōu)于純財(cái)務(wù)指標(biāo)模型。 (4)構(gòu)建了加入Web金融信息情感褒貶程度指標(biāo)的上市公司財(cái)務(wù)危機(jī)動(dòng)態(tài)預(yù)警模型S-EWMA.該預(yù)警模型基于財(cái)務(wù)指標(biāo)的動(dòng)態(tài)面板數(shù)據(jù)ARMA模型而構(gòu)建,能很好地反映財(cái)務(wù)指標(biāo)的時(shí)序特性,又在指數(shù)加權(quán)移動(dòng)平均控制圖中加入了Web金融信息情感褒貶程度指標(biāo),彌補(bǔ)了財(cái)務(wù)指標(biāo)滯后性等缺陷,能夠反映上市公司財(cái)務(wù)危機(jī)逐步演變發(fā)展的動(dòng)態(tài)性及演變趨勢(shì),能夠有效地預(yù)警財(cái)務(wù)危機(jī)發(fā)生的時(shí)點(diǎn)。實(shí)證分析表明,該模型可以較大地提高財(cái)務(wù)危機(jī)預(yù)警的超前性。
[Abstract]:The development of market economy, the competition between companies is increasingly fierce, and the global economic integration, not only bring development opportunities, but also hidden endless crises and risks. For listed companies, and even forced to withdraw from the market because of the special treatment by the financial crisis, not only affect their own survival and development, but also bring huge the economic losses to investors and creditors. Therefore, the financial crisis of the listed companies is accurate, timely, effective early warning, is to promote the development of capital market and the national economy, plays an important role in maintaining social stability.
Study on early warning of financial crisis mainly involves two aspects: the early warning indicators and warning model. The existing research on the early warning index is the choice of the main financial indicators of financial indicators, however due to the lag and easy manipulation of inherent defects, some scholars actively introduce such as macroeconomic variables, corporate governance variables, non-financial indicators of industry variables however, because of the many types of non-financial indicators, data acquisition, and some indicators are difficult to quantify, these are in the early warning of financial crisis in the non obstacle. The introduction of financial indicators and the development of network technology, the emergence of a large number of Web financial information, real-time, it has the characteristics of comprehensive coverage, and easy get, just to make up the non financial indicators are difficult to obtain and not complete, is not comprehensive, and provides a new way for the acquisition of non-financial indicators of financial crisis early warning.
Study on financial crisis early warning model, the existing research results from the traditional statistical model to artificial intelligence model, mostly static prediction model built using cross section data, and the listed company's financial crisis is not a sudden, there is a gradual evolutionary process, static early-warning model does not consider the temporal characteristics of early warning indicators, ignoring the influence of historical data of the early warning results, poor early warning result of the early warning model, it is difficult to promote in the practical application.
This article from the above two aspects, on the one hand, to study how the early warning function Web financial information into the listed company's financial crisis early warning index system and Web financial information index; on the other hand, the dynamic early warning of financial crisis of listed companies. Based on these two aspects, this paper studies the following contents:
(1) the quantification study on Web financial information. Because the Web financial information is basically unstructured text information, so, to put it into the financial crisis early warning index system, it needs to be reasonably quantified, text sentiment content value calculation is a common method of text information based on quantization. Text Web financial information, constructs the financial sector sentiment dictionary presents value calculation method based on fractional morpheme sentiment.
(2) analyzes the relationship between the financial condition of Web financial information of listed companies and the relationship between the financial condition of Web. And financial information of listed companies, this paper mainly studies two aspects. First, through the correlation analysis of the Web financial information index (i.e. information heat and emotional value) relationship with financial index; secondly, the use of Logistic analysis of the Web financial information index on early warning of listed companies will be the impact of ST regression.
(3) examined the effect of Web financial information index of the financial crisis early warning model. LIBSVM were constructed by the hybrid model of pure financial early-warning model and financial index and Web index of the combination of financial information used in this paper, through empirical analysis, we found that the addition of Web financial information indicators, early warning model in advance, stability and efficiency other aspects are greatly improved.
(4) the dynamic early warning of financial crisis of listed companies. This paper uses ARMA model of econometrics, the timing characteristics of the listed company's financial position was fitting; then using the control chart thought on quality management, Web financial information emotion appraise index of the degree of joining EWMA, constructed the S-EWMA dynamic financial crisis warning model of listed company; finally carries on the empirical analysis, comparing with EWMA.
The innovative work of this article is reflected in the following:
(1) put forward the calculation method of morpheme scores of the Web financial information based on the text sentiment. At present, research results of sentiment computation are many, but the calculation method is often affected by seed word selection and coverage of sentiment dictionary and other aspects, and specialized research on emotional financial field text computing has not been found. The proposed method of calculating the morpheme scores of the Web financial information based on the text sentiment, with the field of pertinence, can fully meet the analysis of financial domain sentiment requirements. First, build the financial sector sentiment dictionary will feature the emotional words in the financial field is added to the dictionary, and the scores of emotional morpheme based on the value calculation method solves the problem of covering the emotion dictionary; secondly, in the emotional tendency of sentence and document value calculation, considering the Modified the role of negative words and adverbs file structure of the document sentiment, consider the sentence in the document in different positions of different contributions to the emotional tendencies, which are given different weights, and the connection between the word clause turning, progressive, parallel mode effects tend to love the sense of the sentence will not. Simply calculated and the value of each part of the emotion. Experimental results also verify the validity of this method.
(2) to analyze the correlation between financial information and financial status of Web listed companies. Through the analysis on the relation between financial information and financial status of Web listed companies, Web financial information contained in the text emotion value and financial indicators did not contain information related to the financial situation of listed companies, so the Web financial information emotion value can be used as an important supplement financial indicators of listed companies.
(3) construction of the listed company's financial crisis early warning model of financial indicators and financial indicators combined with the Web information. To construct the financial crisis warning model of listed companies based on the hybrid index Web of financial information and financial index, the empirical results show that the model is effective in early warning, stability and advance is superior to pure the financial index model.
(4) the construction of joining the Web financial information likeness degree of listed company financial crisis early warning model of the S-EWMA. dynamic early-warning model and build dynamic panel data ARMA model based on financial indicators, can well reflect the timing characteristics of financial indicators, and the exponentially weighted moving average control chart with Web financial information likeness the degree of index, make up the lag of financial indicators and other defects, and can reflect the dynamic evolution trend of listed company financial crisis gradually evolved, can effective early warning of financial crisis point. The empirical analysis shows that the model can advance the financial crisis early warning is greatly improved.

【學(xué)位授予單位】：江西財(cái)經(jīng)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：F832.51;F275

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 章之旺,吳世農(nóng);經(jīng)濟(jì)困境、財(cái)務(wù)困境與公司業(yè)績(jī)——基于A股上市公司的實(shí)證研究[J];財(cái)經(jīng)研究;2005年05期

2 劉國(guó)光,王慧敏,張兵;考慮違約距離的上市公司危機(jī)預(yù)警模型研究[J];財(cái)經(jīng)研究;2005年11期

3 王克敏;姬美光;;基于財(cái)務(wù)與非財(cái)務(wù)指標(biāo)的虧損公司財(cái)務(wù)預(yù)警研究——以公司ST為例[J];財(cái)經(jīng)研究;2006年07期

4 曹德芳;夏好琴;;股權(quán)結(jié)構(gòu)變量對(duì)企業(yè)財(cái)務(wù)危機(jī)影響的實(shí)證研究[J];東北大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2006年01期

5 傅榮,吳世農(nóng);我國(guó)上市公司經(jīng)營(yíng)失敗風(fēng)險(xiǎn)的判定分析——BP神經(jīng)網(wǎng)絡(luò)模型和Fisher多類線性判定模型[J];東南學(xué)術(shù);2002年02期

6 萬希寧;王艷;;基于非財(cái)務(wù)指標(biāo)的企業(yè)財(cái)務(wù)危機(jī)模糊預(yù)警模型研究[J];管理學(xué)報(bào);2007年02期

7 劉建國(guó);;多維EWMA控制圖的企業(yè)危機(jī)動(dòng)態(tài)預(yù)警研究[J];工業(yè)工程與管理;2010年05期

8 鄧曉嵐;王宗軍;李紅俠;楊忠誠(chéng);;非財(cái)務(wù)視角下的財(cái)務(wù)困境預(yù)警——對(duì)中國(guó)上市公司的實(shí)證研究[J];管理科學(xué);2006年03期

9 吳世農(nóng),盧賢義;我國(guó)上市公司財(cái)務(wù)困境的預(yù)測(cè)模型研究[J];經(jīng)濟(jì)研究;2001年06期

10 郭鵬飛,孫培源;資本結(jié)構(gòu)的行業(yè)特征:基于中國(guó)上市公司的實(shí)證研究[J];經(jīng)濟(jì)研究;2003年05期

，

本文編號(hào)：1424934