本研究蒐集經濟日報、聯合報及聯合晚報的新聞文章，以中研院的中文斷詞系統進行結構性的處理，研究企業社會責任新聞，對於股價的報酬率是否有正面、負面的影響，而以台灣掛牌的企業為研究的標的(以台灣50為例)。 本研究利用新聞文字，去判斷這個新聞是否與企業社會責任有關，而這次所利用的新聞，是台灣報章媒體的新聞，我們用這些新聞來測試新聞對投資人的投資行為、財富有沒有影響。 本研究發現，正面的企業社會責任新聞帶來不顯著的累積超額負報酬，而負面的企業社會責任新聞，則會帶來顯著的股價宣告效果。這個現象是由於負面的企業社會責任新聞通常較正面的企業社會責任新聞難以被投資人所預期，因此相對正面的企業社會責任新聞，負面的企業責任新聞對於股價宣告效果有較顯著的影響。 接著，本研究依據Michael Porter(2006)的研究，將企業社會責任新聞分為三類(一般、價值維護、價值創造)，我們發現企業社會責任新聞在其中一類，也就是「價值創造」，正面新聞對於股票的報酬有顯著正面影響。在調整了市場報酬並調整交易成本之後，我們發現投資人能利用以下的交易策略獲得超額正報酬。 1. 買入有「價值創造」正面企業社會責任新聞的個股 2. 放空有負面企業社會責任相關新聞、負面企業治理新聞的個股。 綜合以上發現，本論文得到，企業社會責任新聞的傳播，確實影響了股票的報酬率，而投資人也可以因應企業社會責任新聞，來獲得超額正報酬。 / This study is to investigate whether CSR Media coverage has positive and negative impacts on corporate stock returns using Taiwan listed company sample data (0050.TT Taiwan Top 50). We use a simple text-analysis approach to quantify CSR (Corporate Social Responsibility) Chinese news at newspapers to test if CSR news influences investor behavior and shareholder wealth changes. This study discovers that, while positive CSR news bring in insignificant negative cumulative abnormal return, negative CSR news have significant impacts on stock announcement returns. The evidence supports the argument that corporate negative CSR news (compare with positive CSR news) is unexpected by investors and have significant impacts on investor risk concern and results in negative announcement returns. Secondly, we follow Michael Porter (2006), we decompose CSR good news into three categories, and we discover that CSR news related to value creation activities has significant positive stock returns. After we control well-known systematic risk and adjust transaction cost, this study discovers that Investors can earn significant positive returns using either long-only trading strategy for stocks with value-creation CSR good news and short-only trading strategy for bad news on corporate governance issues. Our findings suggest that the CSR information dissemination affects stock returns.

財務報表中的主觀性詞彙往往影響市場中的參與者對於報導公司價值和獲利能力衡量的決策判斷。因此，公司的管理階層往往有高度的動機小心謹慎的選擇用詞以隱藏負面的消息而宣揚正面的消息。然而使用人工方式從文字量極大的財務報表挖掘有用的資訊往往不可行，因此本研究採用人工智慧方法驗證美國財務報表中的主觀性多字詞 (subjective MWEs) 和公司的財務狀況是否具有關聯性。多字詞模型往往比傳統的單字詞模型更能掌握句子中的語意情境，因此本研究應用條件隨機域模型 (conditional random field) 辨識多字詞形式的意見樣式。另外，本研究的實證結果發現一些跡象可以印證一般人對於財務報表的文字揭露往往與真實的財務數字存在有落差的印象；更發現在負向的盈餘變化情況下，公司管理階層通常輕描淡寫當下的短拙卻堅定地承諾璀璨的未來。 / Subjective assertions in financial statements influence the judgments of market participants when they assess the value and profitability of the reporting corporations. Hence, the managements of corporations may attempt to conceal the negative and to accentuate the positive with "prudent" wording. To excavate this accounting phenomenon hidden behind financial statements, we designed an artificial intelligence based strategy to investigate the linkage between financial status measured by annual earnings and subjective multi-word expressions (MWEs). We applied the conditional random field (CRF) models to identify opinion patterns in the form of MWEs, and our approach outperformed previous work employing unigram models. Moreover, our novel algorithms take the lead to discover the evidences that support the common belief that there are inconsistencies between the implications of the written statements and the reality indicated by the figures in the financial statements. Unexpected negative earnings are often accompanied by ambiguous and mild statements and sometimes by promises of glorious future.

University of Macau / Faculty of Social Sciences and Humanities / Department of Chinese

University of Macau / Faculty of Social Sciences and Humanities / Department of Chinese

University of Macau / Faculty of Social Sciences and Humanities / Department of Chinese

本研究欲探究個股新聞影響台灣股票市場之關係，透過蒐集宏達電、台積電與鴻海等三間上市公司從2012年6月至2013年5月的歷史交易資料和個股新聞，使用文字探勘技術找出各新聞內容的特徵，再透過歷史資料、技術分析指標與kNN和2-way kNN演算法將新聞先做分類後分群，建立預測模型，分析新聞對股價漲跌的影響與程度，以及漲跌幅度較高之群集與股價漲跌和轉折的關係。 研究結果發現，加入技術分析指標後能夠提升分類的準確率，而漲跌類別內的分群能夠界定各群集與股價漲跌之間的關係，且漲跌幅度較高之群集的分析則能大幅提升投資準確率至80%左右，而股價轉折點之預測則能提供一個明確的投資進場時間點，並確保當投資人依照此預測模型的結果進行7交易日投資時，可以在風險極低的前提下，穩當且迅速的獲取2.82%至22.03%不等的投資報酬。 / This study investigated the relation that the stock news effect on Taiwan Stock Market. Through collected the historical transaction data and stock news from July, 2012 to May, 2013, and use text mining、kNN Classification and 2-Way kNN Clustering technique analyzing the stock news, build a forecast model to analyze the degree of news effect on the stock price, and find the relation between the cluster which has great degree and the reversal points of stock price. The result shows that using the change range and Technical Indicator rise classification’s accuracy, and clustering in the ”up” group and “down” group can identify the range stock price move, and rise the invested accuracy up to about 80 percent. The forecast of reversal points of stock price offers a specific time to invest, and insure the investors who execute a 7 trading day investment depend on this model can get 2.82 to 22.03 percent return reliably and quickly with low risk.

各種行動裝置服務不僅便利了生活，也讓資訊的傳遞更加即時且無界。2012年起，五家媒體藉助行動通訊軟體LINE在台灣的高人氣，每日固定推播四則新聞，總訂戶數至今突破450萬人，儼然成為一個新興的新聞傳播渠道。 本研究以情境理論的觀點，質化的使用者日誌記錄法和深度訪談法為主，理解使用者在不同情境下使用推播新聞的行為，並透過HTML5文字雲分析機，歸納出各家媒體推播內容的樣貌和趨勢。情境分析構面包含接收與閱讀情境下的「實體環境」、「社交環境」、「資訊環境」、「先前狀態」和「時間的影響」等；另再針對使用過程中面臨的「人機互動情境」綜合分析使用者的體驗。 這些情境因素不僅各自影響媒介使用的動機和行為，也會與新聞內容相互加強（或制約）吸引力，端賴哪方拉力（或推力）較強。根據訪談結果，「新聞內容」的影響力似乎又更為關鍵。受訪者普遍認為推播新聞的即時性和重要性偏低，新聞價值未能滿足期待，導致對LINE推播新聞的需要性和依賴性偏低。 未來業者可考慮設立不同的「主題式官方帳號」，提供針對性的內容；或者在目前的官方帳號中，增加一日新聞類型的多元性以滿足更多人的需求，就看媒體如何定位自家官方帳號的角色。此外，在發揮新聞標題創意的同時，仍應與內文保持一致，避免造成期待上的落差。不斷強化內容品質，並考量主要受眾的使用情境，可望改善體驗不佳的問題。 本研究以情境理論的觀點，開啟了「推播新聞」的學術研究基礎，並充實行動新聞領域的實證研究經驗，希望提供未來的研究者和新聞從業人員，一個了解推播新聞使用行為的先例。 / Mobile devices and services facilitate our lives, and also assist in delivering information more freely and immediately. Since 2012, five companies send four pieces of news daily through “LINE”, which is the most popular mobile instant messaging application in Taiwan. Nowadays, LINE becomes an emerging news channel, with over 450 million subscribers in total. This study is mainly based on the context theory, by means of diary method and in-depth interviews, to understand users’ behavior of push notifications news in different contexts, from news receiving aspect, reading aspect and human-computer interaction aspect. Besides, analyzing the news headlines by “HTML5 Text Analyzer” to explore the features of different media. Research found that users’ behavior and attitude influenced not only by contextual factors, but also by the value of content. Moreover, the effect of contextual factors and content would be reinforcing (or restraining) mutually, depends which one influence users’ behavior and attitude more crucially. According to respondents’ feedback, the value of push notification news, such as immediacy and importance, were far from their expectations. News editors may plan to set up more than one official account to reach target audience; or to increase the diversity of daily news by existing accounts, making effort to meet demand of more audience. In addition, the headline should be more concordant with the content of the news. Keep improving the quality of content, taking account of context factors while pushing news, may improve users’ experience.

因網際網路帶來的便利性與即時性，網路新聞成為社會大眾吸收與傳遞新聞資訊的重要管道之一，而累積的巨量新聞亦可反映出社會輿論對某特定新聞議題之即時反應、熱門程度以及情緒走向等。 因此，本研究期望借由意見探勘與情緒分析技術，從特定領域新聞中挖掘出有價值的關聯，並結合傳統機器學習建立一個房地產市場的預測模式，提供購屋決策的參考依據。 本研究搜集99年1月1日至103年6月30日共1,1150筆房地產新聞，以及8,165件捷運週邊250公尺內房屋買賣交易資料，運用意見探勘萃取意見詞彙進行情緒分析，並建立房市情緒與成交價量時間序列，透過半年移動平均、二次移動平均及成長斜率，瞭解社會輿情對房市行情抱持樂觀或悲觀，分析社會情緒與實際房地產成交間關聯性，以期能找出房地產買賣時機點，並進一步結合情緒及房地產的環境影響因素，藉由支援向量機建立站點房市的預測模型。 實證結果中，本研究發現房市情緒與成交價量之波動有一定的週期與相關性，且新捷運開通前一年將連帶影響整體捷運房市波動，當成交線穿越情緒線且斜率同時向上時，可做為適當的房市進場時機點。而本研究針對站點情緒與環境變數所建立之預測模型，其預測新捷運線站點之平均準確率為69.2％，而預測新捷運線熱門站點之準確率為78％，顯示模型於預測熱門站點上具有不錯的預測能力。 / Nowadays, E-News have become an important way for people to get daily information. These enormous amounts of news could reflect public opinions on a particular attention or sentiment trends in news topics. Therefore, how to use opinion mining and sentiment analysis technology to dig out valuable information from particular news becomes the latest issue. In this study, we collected 1,1150 house news and 8,165 house transaction records around the MRT stations within 250 meters over the last five years. We extracted the emotion words from the news by manipulating opinion mining. Furthermore, we built moving average lines and the slope of the moving average in order to explore the relationship and entry point between public opinion and housing market. In conclusion, we indicated that there is a high correlation between the news sentiment and housing market. We also uses SVM algorithm to construct a model to predict housing hotspots. The results demonstrate that the SVM model reaches average accuracy at 69.2% and the model accuracy increases up to 78% for predicting housing hotspots. Besides, we also provide investors with a basis of entry point into the housing market by utilizing the moving average cross overs and slopes analysis and a better way of predicting housing hotspots.

近年來科技、網路以及儲存媒介的發達，產生的資料量呈現爆炸性的成長，也宣告了巨量資料時代的來臨。擁有巨量資料代表了不必再依靠傳統抽樣的方式來蒐集資料，分析數據也不再有資料收集不足以致於無法代表母題的限制。突破傳統的限制後，巨量資料的精隨在於如何從中找出有價值的資訊。 以擁有大量輿論和人際互動資訊的社群網站為例，就有相關學者研究其情緒與股價具有正相關性，本研究也試著利用同樣具有巨量資料特性的網路新聞，抓取中央新聞社2013年7月至2014年5月之經濟類新聞共計30,879篇，結合新聞主題偵測與追蹤技術及情感分析，利用新聞事件相似的概念，透過連結匯聚成網絡並且分析新聞的情緒和股價指數的關係。 研究結果顯示，新聞事件間可以連結成一特定新聞主題，且能在龐大的網絡中找出不同的新聞主題，並透過新聞主題之連結產生新聞主題脈絡。對此提供一種新的方式來迅速了解巨量新聞內容，也能有效的回溯新聞主題及新聞事件。 在新聞情緒和股價指數方面，研究發現新聞情緒影響了股價指數之波動，其相關係數達到0.733562；且藉由情緒與心理線及買賣意願指標之比較，顯示新聞的情緒具有一定的程度能夠成為股價判斷之參考依據。 / In recent years, the technology, network, and storage media developed, the amount of generated data with the explosive growth, and also declared the new era of big data. Having big data let us no longer rely on the traditional sample ways to collect data, and no longer have the issue that could not represent the population which caused by the inadequate data collection. Once we break the limitations, the main spirit of big data is how to find out the valuable information in big data. For example, the social network sites (SNS) have a lot of public opinions and interpersonal information, and scholars have founded that the emotions in SNS have a positive correlation with stock prices. Therefore, the thesis tried to focus on the news which have the same characteristic of big data, using the web crawl to catch total of 30,879 economics news articles form the Central News Agency, furthermore, took the “Topic Detection & Tracking” and “Sentiment Analysis” technology on these articles. Finally, based on the concept of the similarity between news articles, through the links converging networks and analyze the relevant between news sentiment and stock prices. The results shows that news events can be linked to specific news topics, identify different news topics in a large network, and form the news topic context by linked news topics together. The thesis provides a new way to quickly understand the huge amount of news, and backtracking news topics and news event with effective. In the aspect of news sentiment and stock prices, the results shows that the news sentiments impact the fluctuations of stock prices, and the correlation coefficient is 0.733562. By comparing the emotion with psychological lines & trading willingness indicators, the emotion is better than the two indicators in the stock prices determination.

全球智慧型手機的出貨量持續提升，且熱門市集的App下載次數紛紛突破500億次。而在iOS和Android手機App市集中，App的評價和評論對App在市集的排序有很大的影響；對於App開發者而言，透過評論確實可掌握使用者的需求，並在產生抱怨前能快速反應避免危機。然而，每日多達上百篇的評論，透過人力逐篇查看，不止耗費時間，更無法整合性的瞭解使用者的需求與問題。 文字情感分析通常會使用監督式或非監督式的方法分析文字評論，其中監督式方法被證實透過簡單的文件量化方法就可達到很高的正確率。但監督式方法有無法預期未知趨勢的限制，且需要進行耗費人力的文章類別標注工作。 本研究透過情感傾向和熱門關注議題兩個面向來分析App評論，提出一個混合非監督式與監督式的中文情感分析方法。我們先透過非監督式方法標注評論類別，並作視覺化整理呈現，最後再用監督式方法建立分類模型，並驗證其效果。 在實驗結果中，利用中文詞彙網路所建立的情感詞集，確實可用來判斷評論的正反情緒，唯判斷負面評論效果不佳需作改善。在議題擷取方面，嘗試使用兩種不同分群方法，其中使用NPMI衡量字詞間關係強度，再配合社群網路分析的Concor方法結果有不錯的成效。最後在使用監督式學習的分類結果中，情感傾向的分類正確率達到87%，關注議題的分類正確率達到96%，皆有不錯表現。 本研究利用中文詞彙網路與社會網路分析，來發展一個非監督式的中文類別判斷方法，並建立一個中文情感分析的範例。另外透過建立全面性的視覺化報告來瞭解使用者的正反回饋意見，並可透過分類模型來掌握新評論的內容，以提供App開發者在市場上之競爭智慧。 / While the number of smartphone shipment is continuesly growing, the number of App downloads from the popular app markets has been already over 50 billion. By Apple App Store and Google Play, ratings and reviews play a more important role in influencing app difusion. While app developers can realize users’ needs by app reviews, more than thousands of reviews produced by user everday become difficult to be read and collated. Sentiment Analysis researchs encompass supervised and unsupervised methods for analyzing review text. The supervised learning is proven as a useful method and can reach high accuracy, but there are limits where future trend can not be recognized and the labels of individual classes must be made manually. We concentrate on two issues, viz Sentiment Orientation and Popular Topic, to propose a Chinese Sentiment Analysis method which combines supervised and unsupervised learning. At First, we use unsupervised learning to label every review articles and produce visualized reports. Secondly, we employee supervised learning to build classification model and verify the result. In the experiment, the Chinese WordNet is used to build sentiment lexicon to determin review’s sentiment orientation, but the result shows it is weak to find out negative review opinions. In the Topic Extraction phase, we apply two clustering methods to extract Popular Topic classes and its result is excellent by using of NPMI Model with Social Network Analysis Method i.e. Concor. In the supervised learning phase, the accuracy of Sentiment Orientation class is 87% and the accuracy of Popular Topic class is 96%. In this research, we conduct an exemplification of the unsupervised method by means of Chinese WorkNet and Social Network Analysis to determin the review classes. Also, we build a comprehensive visualized report to realize users’ feedbacks and utilize classification to explore new comments. Last but not least, with Chinese Sentiment Analysis of this research, and the competitive intelligence in App market can be provided to the App develops.