本篇研究專注於首次公開發行公司上市櫃初始交易日之異常報酬與新聞情緒兩 者間之關係。本研究建立情緒字典以判別新聞之正負情緒,並過濾出與首次公開發 行有關之新聞,利用本研究建立之情緒字典以過濾出正負情緒之詞組。利用正負情 緒詞組數量計算出三種新聞情緒變數,並採實證研究方法檢測三種新聞情緒變數與 首次公開發行公司之初始交易日之異常報酬兩者間之關係。根據本研究之實證結果, 發現初始交易日之前的新聞能影響首次公開發行之異常報酬,而相關新聞之情緒語 調亦和異常報酬有關。此外,本研究亦檢測三種情緒變數和三種傳統變數之交乘項 對異常報酬之影響,發現公司規模大小與首日交易量與情緒變數之交乘項會對初始 交易日之異常報酬有影響。總言論之,本研究對新聞會影響首次公開發行初始交易 日之異常報酬提供了實證證據。 / This study focuses on the relation between IPOs’ abnormal returns on initial trading days and news sentiment. To identify the tone of news, sentiment dictionary was established for this study, and news regarding IPO firms was picked out to count positive and negative words and phrases based on the sentiment dictionary. Using quantities of positive and negative words and phrases, three news variables were adopted and calculated. And linear regression was utilized to investigate the relation between IPOs’ abnormal returns on initial trading days and news sentiment. According to empirical results, I find that news prior to the IPO’s initial trading day can affect IPOs’ abnormal returns. The number of negative words and phrases is negatively related to the abnormal returns; the tone of news is positively related to the abnormal returns. Furthermore, I also investigated whether interaction terms of news variables and three control variables are related to abnormal returns on IPOs’ initial trading days. I find that interaction terms of the natural logarithm of firm size and two news variables and interaction terms of the natural logarithm of first-day trading volume and two news variables are related to abnormal returns. Overall, there is evidence that news can influence IPOs’ abnormal returns on initial trading days.

本論文的目標是利用文本情緒分析技巧，針對美國上市公司的財務報表進行以句子為單位的風險評估。過去的財報文本分析研究裡，大多關注於詞彙層面的風險偵測。然而財務文本中大多數的財務詞彙與前後文具有高度的語意相關性，僅靠閱讀單一詞彙可能無法完全理解其隱含的財務訊息。本文將研究層次由詞彙拉升至句子，根據基於嵌入概念的~fastText~與~Siamese CBOW~兩種句子向量表示法學習模型，利用基於嵌入概念模型中，使用目標詞與前後詞彙關聯性表示目標詞語意的特性，萃取出財報句子裡更深層的財務意涵，並學習出更適合用於財務文本分析的句向量表示法。實驗驗證部分，我們利用~10-K~財報資料與本文提出的財務標記資料集進行財務風險分類器學習，並以傳統詞袋模型（Bag-of-Word）作為基準，利用精確度（Accuracy）與準確度（Precision）等評估標準進行比較。結果證實基於嵌入概念模型的表示法在財務風險評估上比傳統詞袋模型有著更準確的預測表現。由於近年大數據時代的來臨，網路中的資訊量大幅成長，依賴少量人力在短期間內分析海量的財務資訊變得更加困難。因此如何協助專業人員進行有效率的財務判斷與決策，已成為一項重要的議題。為此，本文同時提出一個以句子為分析單位的財報風險語句偵測系統~RiskFinder~，依照~fastText~與~Siamese CBOW~兩種模型，經由~10-K~財務報表與人工標記資料集學習出適當的風險語句分類器後，對~1996~至~2013~年的美國上市公司財務報表進行財報句子的自動風險預測，讓財務專業人士能透過系統的協助，有效率地由大量財務文本中獲得有意義的財務資訊。此外，系統會依照公司的財報發布日期動態呈現股票交易資訊與後設資料，以利使用者依股價的時間走勢比較財務文字型與數值型資料的關係。 / The main purpose of this paper is to evaluate the risk of financial report of listed companies in sentence-level. Most of past sentiment analysis studies focused on word-level risk detection. However, most financial keywords are highly context-sensitive, which may likely yield biased results. Therefore, to advance the understanding of financial textual information, this thesis broadens the analysis from word-level to sentence level. We use two sentence-level models, fastText and Siamese-CBOW, to learn sentence embedding and attempt to facilitate the financial risk detection. In our experiment, we use the 10-K corpus and a financial sentiment dataset which were labeled by financial professionals to train our financial risk classifier. Moreover, we adopt the Bag-of-Word model as a baseline and use accuracy, precision, recall and F1-score to evaluate the performance of financial risk prediction. The experimental results show that the embedding models could lead better performance than the Bag-of-word model. In addition, this paper proposes a web-based financial risk detection system which is constructed based on fastText and Siamese CBOW model called RiskFinder. There are total 40,708 financial reports inside the system and each risk-related sentence is highlighted based on different sentence embedding models. Besides, our system also provides metadata and a visualization of financial time-series data for the corresponding company according to release day of financial report. This system considerably facilitates case studies in the field of finance and can be of great help in capturing valuable insight within large amounts of textual information.

過往對於情緒分析的研究顯少聚焦在讀者情緒，往往著眼於筆者情緒之研究。讀者情緒是指讀者閱讀文章後產生之情緒感受。然而相同一篇文章可能會引起讀者多種情緒反應，甚至產生與筆者迥異之情緒感受，也突顯其讀者情緒分析存在更複雜的問題。本研究之目的在於辨識讀者閱讀文章後之切確情緒，而文件分類的方法能有效地應用於讀者情緒偵測的研究，除了能辨識出正確的讀者情緒之外，並且能保留讀者情緒文件之相關內容。然而，目前的資訊檢索系統仍缺乏對隱含情緒之文件有效的辨識能力，特別是對於讀者情緒的辨識。除此之外，基於機器學習的方法難以讓人類理解，也很難查明辨識失敗的原因，進而無法了解何種文章引發讀者切確的情緒感受。有鑑於此，本研究提出一套基於語意框架(frame-based approach, FBA)之讀者情緒偵測研究的方法，FBA能模擬人類閱讀文章的方式外，並且可以有效地建構讀者情緒之基礎知識，以形成讀者情緒的知識庫。FBA具備高自動化抽取語意概念的基礎知識，除了利用語法結構的特徵，我們進一步考量周邊語境和語義關聯，將相似的知識整合成具有鑑別力之語意框架，並且透過序列比對(sequence alignment)的方式進行讀者情緒文件之匹配。經實驗結果顯示證明，本研究方法能有效地運用於讀者情緒偵測之相關研究。 / Previous studies on emotion classification mainly focus on the writer's emotional state. By contrast, this research emphasizes emotion detection from the readers' perspective. The classification of documents into reader-emotion categories can be applied in several ways, and one of the applications is to retain only the documents that cause desired emotions for enabling users to retrieve documents that contain relevant contents and at the same time instill proper emotions. However, current IR systems lack of ability to discern emotion within texts, reader-emotion has yet to achieve comparable performance. Moreover, the pervious machine learning-based approaches are generally not human understandable, thereby, it is difficult to pinpoint the reason for recognition failures and understand what emotions do articles trigger in their readers. We propose a flexible semantic frame-based approach (FBA) for reader's emotion detection that simulates such process in human perception. FBA is a highly automated process that incorporates various knowledge sources to learn semantic frames that characterize an emotion and is comprehensible for humans from raw text. Generated frames are adopted to predict readers' emotion through an alignment-based matching algorithm that allows a semantic frame to be partially matched through a statistical scoring scheme. Experiment results demonstrate that our approach can effectively detect readers' emotion by exploiting the syntactic structures and semantic associations in the context as well as outperforms currently well-known statistical text classification methods and the stat-of-the-art reader-emotion detection method.

社群網站使用者不分年齡，幾乎沒有人不在這虛擬社交的浪潮上。儘管如此， 社群網站的交往卻不如現實般，社群中的絕大多數的內容是由少數發言者貢獻， 從來不發言的潛水者則佔了使用者基數的大部分。 本研究使用沈默螺旋理論的意見一致性概念與多種潛水動機作連接，藉此探 討發言者言論如何影響潛水者的動機選擇以及潛水行為表現。除此外，本研究藉 由同時使用社群聆聽技術和調查法作為研究方法，試圖以主、客觀區分兩種方法 並比較各自的益處和限制，也對社群聆聽技術只能使用發言者言論作為分析資料 來源的先天限制做出初步探討。 本研究收集到 599 份有效問卷和 285 篇社群網站文章，研究結果發現害怕被 孤立、社會性散漫兩種潛水動機完全中介了意見一致性對潛水行為的效果。主、 客觀研究方法的測量結果顯著相關，且對潛水動機之中介效果有相同預測能力。 / It is hard to find one had no experience using social networks in any age ranges. However, most of social network members are lurkers who barely post or comment to express their opinion. On the other hand, little regular posters contribute most content in every virtual society. This study used the concept of opinion congruency in spiral of silence theory to link up multiple lurking motives found by past studies in order to clarify how posters’ texts influence lurking motives and behavior. Besides, for the purpose of comparing pros and cons between social listening and survey, this study adopted both research methods to measure major opinion in discussion threads wherea seprated the two methods into subjective and objective ones. Also, this study would have preliminary discuss about the fact of limited analytical source of social listening. Collected 599 valid surveys and 285 social network discuss thread text, the result found that opinion congruency negatively influenced both lurking motives which positively influenced lurking behavior. The result also found that the subjective and objective research methods in this study were significantly related, and shared same predictive ability on both lurking motives’ mediated effect.

隨著Web 2.0社群媒體服務的普及化，越來越多的民眾開始運用網際網路發表自身對於政府治理的需求與看法，大量的民意資訊在網絡的交互連結下，迅速集結成可觀的網路輿情。由於網路輿情具備巨量資料的特性，使得當前各政府部門熟悉的分析方法，似乎產生適用上的困難。因而網路輿情分析的出現，成為當前政府洞察民意的新興工具。更重要的是，如何運用網路輿情分析進一步與政策面產生實質的連結，如探究網路輿情分析當中情緒分析對於政策立場解讀的可能性，對公共管理者而言更為重要。再者，網路輿情分析目前尚缺乏一套檢測方法來驗證其分析結果的信效度。因此，本研究的目的在於，運用網路輿情分析所撈取的輿情資料，比較新聞網站、社群網站、討論區及部落格四類來源在情緒分析與立場分析之差異，最後運用情緒與立場來解讀網路輿情。 研究設計，本文採用次級資料分析法及內容分析法，次級資料來自2014年行政院國發會委託政治大學蕭乃沂教授所主持的「政府應用巨量資料精進公共服務與政策分析之可行性研究」，本文以「自由經濟示範區政策」作為個案分析。研究發現，在立場分析方面，新聞網站及部落格是支持立場的言論最多；而社群網站及討論區則是反對立場的言論最多。情緒分析方面，四類來源皆以負向情緒的言論為主，正向情緒的言論相對少；透過情緒與立場的交叉分析顯示，機器會產生兩類誤判情形，第一類誤判是被機器判讀是正向情緒，但人工判讀為反對立場的言論，以社群網站的來源居多；第二類誤判是被機器判讀是負向情緒，但人工判讀為支持立場的言論，以新聞網站的來源居多。 依此研究發現，本文建議未來實務者在應用網路輿情分析時，不能僅以整體網路輿情分析的結果輕斷，必要時應將不同網路言論來源個別觀察，特別是當負向情緒的輿論出現時，應優先留意社群網站的動向。此外，針對輿情的高峰期也可對照新聞網站的分析結果，了解是否受到特定新聞報導的牽動而引起網民的討論。值得注意的是，針對社群網站中正向情緒的輿論，實務者也不能過於樂觀，因為部份正向情緒的言論可能是帶有網民「拐彎抹角」的反對。 / In the era of Web 2.0, more and more people express their opinions for public governance on the Internet. Massive public opinions are quickly generated. However, it seems difficult to analyze for government because of the feature of big data. Internet public opinion analysis(IPOA) has become new analytical methods for public managers. The purpose of this study is to use IPOA to mine large amounts of policy opinions and conduct sentiment analysis(SA) comparing with political positions analysis(PPA) in the news sites, forums, social networking sites and blogs. Finally, interpreting the network of public opinion by SA and PPA. Secondary data analysis and content analysis are applied. Secondary data collected by the Research, National Development council, the Executive Yuan. A Case Study of Free Economic Pilot Zones Policy is selected. In terms of PPA, the results reveal more supporting political opinions in the news sites and blogs. And more opposing political opinions in the social networking sites and forums. In terms of SA, four types of sources are negative emotions in large part. By cross-analysis, SA and PPA have difference on results. There will be two types of false judgments by SA with machine. One is judged positive emotion by machine, but opposing political opinions by coders, such as social networking sites. The other is judged negative emotion by machine, but supporting political opinions by coders, such as news sites. From this study, author suggests that practitioners should separately make the necessary observation of various networks rather than only determine on overall results as using IPOA. Especially, giving priority to the social networking sites when the opposing political opinions emerge. Moreover, the peak period for opposing political opinions in the social networking sites can be compared with the events in the news sites. It is noteworthy that practitioners should pay attention to the partial positive comments in social network sites with“irony”remarks.