No description available.

No description available.

網際網路時代資訊接收的便利性，使得大眾容易接收到媒體所發布的媒體資訊，而這些資料具含的意見詞彙間接反應出群眾對特定主題的情緒傾向。在針對房地產的媒體當中，當特定區域的房地產市場具有良好的發展空間而成為交易熱區時，這些針對特定區域且帶含情緒的房市篇章報導或其他影響房市之相關新聞以及廣告往往會影響我們的購屋決策。 本研究將以桃園市及台中市-兩個近五年來台灣房市較為熱門的區域作為研究區域進行分析及研究，期望找出在短期時間新聞輿情及廣告和房市交易價量的相關性以及會影響該房地產市場之因素。首先蒐集桃園市及台中市的實價登錄的房地產交易資料以及廣告後，運用文字探勘分析房市整體輿情與兩都市房地產價量之關聯性，再將新聞分群後找出特徵詞，個別建立時間序列來了解各種情緒及房地產價量的共同移動性，並結合廣告投入量找出房地產市場價量以及影響因素的領先關係。並透過自建的類神經網路模型建立針對桃園市和台中市的交易量預測模型以及針對特定房市熱門區域-青埔和七期的交易量預測模型，並透過計算輸入變數的權重總和來判別新聞情緒對於房地產成交價量的影響程度。 研究首先提供了對於新聞情緒的分類包含區域經濟情緒、區域社會情緒、區域環境情緒、區域政治情緒、稅制情緒、選舉情緒。接著進行時間序列分析指出總情緒序列與成交量的時間序列相關係數都有高於70%以上，桃園市成交量與桃園市情緒的相關係數為0.73，台中市成交量與台中市情緒的相關係數為0.81，皆呈現高度正相關，顯示桃園及台中的房市交易量與情緒現存在高度相關性。在特定新聞類別當中，透過兩個城市的相關係數比對顯示稅制新聞情緒，區域環境相關情緒，區域社會相關情緒，以上三個情緒跟房市的交易量共同移動較為明顯，相關係數皆在0.5左右甚至以上，可見這些類別的新聞能夠適時反映大眾對於特定區域的房地產的看好及看壞。在此階段也透過領先指標驗證了情緒以及廣告是會領先房市交易量，桃園以及台中兩個區域都有情緒領先交易量一個月的現象。針對特定區域的交易量研究包含青埔特區及七期重劃區，也發現到兩地的交易量高峰前一至兩個月都有一波廣告的高峰。 而在類神經網路模型方面的研究結果能夠良好地預測漲跌趨勢，利用桃園資料進行訓練並以台中資料做為測試的模型在19次的漲跌中預測出17次，而將百分之七十的桃園及台中混合資料進行訓練並其餘百分之三十做為測試的模型結果也成功在14次漲跌中預測出10次，顯示模型效果預測能力良好，並透過將輸入權重加總的方式來衡量各輸入變數的影響程度，研究結果指出總情緒，稅制情緒量，區域環境情緒量與兩地房地產市場交易量最有關聯且影響最重。最後利用時間序列得知廣告高峰會領先總交易高峰一至兩個月的特性，利用從2012年10月至2016年2月的青埔特區資料及2012年10月至2013年12月的七期重劃區資料混合進行訓練並以2014年1月至2016年2月七期重劃區資料做為測試資料的模型能夠有效在兩年內預測中三次交易高峰，顯示該模型能透過預測出下一期的廣告投入量做為中介變數進而推估出交易量高峰的時間透過此模型可在未來應用於相關政策投入市場後對市場交易量的影響，也能夠快速有效的得到預測結果，而在針對特定市場我們也可以透過預測廣告以及運用廣告為交易量的領先特性來了解在近期何時會有交易量高峰，如能配合了解市場輿情脈絡，可為房屋仲介以及建商在更精確的時間點投放廣告時機點達到廣告的最大效益。

Ce travail présente une étude linguistique des expressions d'opinions issues de différentes sources dans des textes en espagnol. Le travail comprend la définition d'un modèle pour les prédicats d'opinion et leurs arguments (la source, le sujet et le message), la création d'un lexique de prédicats d'opinions auxquels sont associées des informations provenant du modèle et la réalisation de trois systèmes informatiques.Le premier système, basé sur des règles contextuelles, obtient de bons résultats pour le score de F-mesure partielle: prédicat, 92%; source, 81%; sujet, 75%; message, 89%, opinion, 85%. En outre, l'identification de la source donne une valeur de 79% de F-mesure exacte. Le deuxième système, basé sur le modèle Conditional Random Fields (CRF), a été développé uniquement pour l'identification des sources, donnant une valeur de 76% de F-mesure exacte. Le troisième système, qui combine les deux techniques (règles et CRF), donne une valeur de 83% de F-mesure exacte, montrant ainsi que la combinaison permet d'obtenir des résultats intéressants.En ce qui concerne l'identification des sources, notre système, comparé à des travaux réalisés sur des corpus d'autres langues que l'espagnol, donne des résultats très satisfaisants. En effet ces différents travaux obtiennent des scores qui se situent entre 63% et 89,5%.Par ailleurs, en sus des systèmes réalisés pour l'identification de l'opinion, notre travail a débouché sur la construction de plusieurs ressources pour l'espagnol : un lexique de prédicats d'opinions, un corpus de 13000 mots avec des annotations sur les opinions et un corpus de 40000 mots avec des annotations sur les prédicats d'opinion et les sources. / This work presents a study of linguistic expressions of opinion from different sources in Spanish texts. The work includes the definition of a model for opinion predicates and their arguments (source, topic and message), the creation of a lexicon of opinion predicates which have information from the model associated, and the implementation of three systems.The first system, based on contextual rules, gets good results for the F-measure score (partial match): predicate, 92%; source, 81%; topic, 75%; message, 89%; full opinion, 85%. In addition, for source identification the F-measure for exact match is 79%. The second system, based on Conditional Random Fields (CRF), was developed only for the identification of sources, giving 76% of F-measure (exact match). The third system, which combines the two techniques (rules and CRF), gives a value of 83% of F-measure (exact match), showing that the combination yields interesting results.As regards the identification of sources, our system compared to other work developed for languages ​other than Spanish, gives very satisfactory results. Indeed these works had scores that fall between 63% and 89.5%.Moreover, in addition to the systems made for the identification of opinions, our work has led to the construction of several resources for Spanish: a lexicon of opinion predicates, a 13,000 words corpus with opinions annotated and a 40,000 words corpus with opinion predicates end sources annotated.

Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2015-05-04T17:25:43Z No. of bitstreams: 1 Rodrigo Morais.pdf: 5083865 bytes, checksum: 69563cc7178422ac20ff08fe38ee97de (MD5) / Made available in DSpace on 2015-05-04T17:25:43Z (GMT). No. of bitstreams: 1 Rodrigo Morais.pdf: 5083865 bytes, checksum: 69563cc7178422ac20ff08fe38ee97de (MD5) Previous issue date: 2013 / Nenhuma / A área de Mineração de Opiniões e Análise de Sentimentos surgiu da necessidade de processamento automatizado de informações textuais referentes a opiniões postadas na web. Como principal motivação está o constante crescimento do volume desse tipo de informação, proporcionado pelas tecnologia trazidas pela Web 2.0, que torna inviável o acompanhamento e análise dessas opiniões úteis tanto para usuários com pretensão de compra de novos produtos quanto para empresas para a identificação de demanda de mercado. Atualmente, a maioria dos estudos em Mineração de Opiniões e Análise de Sentimentos que fazem o uso de mineração de dados se voltam para o desenvolvimentos de técnicas que procuram uma melhor representação do conhecimento e acabam utilizando técnicas de classificação comumente aplicadas, não explorando outras que apresentam bons resultados em outros problemas. Sendo assim, este trabalho tem como objetivo uma investigação empírica e comparativa da aplicação do modelo clássico de Redes Neurais Artificiais (RNAs), o multilayer perceptron , no problema de Mineração de Opiniões e Análise de Sentimentos. Para isso, bases de dados de opiniões são definidas e técnicas de representação de conhecimento textual são aplicadas sobre essas objetivando uma igual representação dos textos para os classificadores através de unigramas. A partir dessa reresentação, os classificadores Support Vector Machines (SVM), Naïve Bayes (NB) e RNAs são aplicados considerandos três diferentes contextos de base de dados: (i) bases de dados balanceadas, (ii) bases com diferentes níveis de desbalanceamento e (iii) bases em que a técnica para o tratamento do desbalanceamento undersampling randômico é aplicada. A investigação do contexto desbalanceado e de outros originados dele se mostra relevante uma vez que bases de opiniões disponíveis na web normalmente apresentam mais opiniões positivas do que negativas. Para a avaliação dos classificadores são utilizadas métricas tanto para a mensuração de desempenho de classificação quanto para a de tempo de execução. Os resultados obtidos sobre o contexto balanceado indicam que as RNAs conseguem superar significativamente os resultados dos demais classificadores e, apesar de apresentarem um grande custo computacional para treinamento, proporcionam tempos de classificação significantemente inferiores aos do classificador que apresentou os resultados de classificação mais próximos aos dos resultados das RNAs. Já para o contexto desbalanceado, as RNAs se mostram sensíveis ao aumento de ruído na representação dos dados e ao aumento do desbalanceamento, se destacando nestes experimentos, o classificador NB. Com a aplicação de undersampling as RNAs conseguem ser equivalentes aos demais classificadores apresentando resultados competitivos. Porém, podem não ser o classificador mais adequado de se adotar nesse contexto quando considerados os tempos de treinamento e classificação, e também a diferença pouco expressiva de acerto de classificação. / The area of Opinion Mining and Sentiment Analysis emerges from the need for automated processing of textual information about reviews posted in the web. The main motivation of this area is the constant volume growth of such information, provided by the technologies brought by Web 2.0, that makes impossible the monitoring and analysis of these reviews that are useful for users, who desire to purchase new products, and for companies to identify market demand as well. Currently, the most studies of Opinion Mining and Sentiment Analysis that make use of data mining aims to the development of techniques that seek a better knowledge representation and using classification techniques commonly applied and they not explore others classifiers that work well in other problems. Thus, this work aims a comparative empirical research of the ap-plication of the classical model of Artificial Neural Networks (ANN), the multilayer perceptron, in the Opinion Mining and Sentiment Analysis problem. For this, reviews datasets are defined and techniques for textual knowledge representation applied to these aiming an equal texts rep-resentation for the classifiers. From this representation, the classifiers Support Vector Machines (SVM), Naïve Bayes (NB) and ANN are applied considering three data context: (i) balanced datasets, (ii) datasets with different unbalanced ratio and (iii) datasets with the application of random undersampling technique for the unbalanced handling. The unbalanced context inves-tigation and of others originated from it becomes relevant once datasets available in the web ordinarily contain more positive opinions than negative. For the classifiers evaluation, metrics both for the classification perform and for run time are used. The results obtained in the bal-anced context indicate that ANN outperformed significantly the others classifiers and, although it has a large computation cost for the training fase, the ANN classifier provides classification time (real-time) significantly less than the classifier that obtained the results closer than ANN. For the unbalanced context, the ANN are sensitive to the growth of noise representation and the unbalanced growth while the NB classifier stood out. With the undersampling application, the ANN classifier is equivalent to the others classifiers attaining competitive results. However, it can not be the most appropriate classifier to this context when the training and classification time and its little advantage of classification accuracy are considered.

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.

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.

<p>Language “in the wild” is complex and ambiguous and relies on a shared understanding of the world for its interpretation. Most current natural language processing methods represent language by learning word co-occurrence patterns from massive amounts of linguistic data. This representation can be very powerful, but it is insufficient to capture the meaning behind written and spoken communication. </p> <p> </p> <p>In this dissertation, I will motivate neural-symbolic representations for dealing with these challenges. On the one hand, symbols have inherent explanatory power, and they can help us express contextual knowledge and enforce consistency across different decisions. On the other hand, neural networks allow us to learn expressive distributed representations and make sense of large amounts of linguistic data. I will introduce a holistic framework that covers all stages of the neural-symbolic pipeline: modeling, learning, inference, and its application for diverse discourse scenarios, such as analyzing online discussions, mining argumentative structures, and understanding public discourse at scale. I will show the advantages of neural-symbolic representations with respect to end-to-end neural approaches and traditional statistical relational learning methods.</p> <p><br></p> <p>In addition to this, I will demonstrate the advantages of neural-symbolic representations for learning in low-supervision settings, as well as their capabilities to decompose and explain high-level decision. Lastly, I will explore interactive protocols to help human experts in making sense of large repositories of textual data, and leverage neural-symbolic representations as the interface to inject expert human knowledge in the process of partitioning, classifying and organizing large language resources. </p>

The overall aim of this thesis was to identify and analyze good innovation management practices in Sweden’s most innovative large companies, excluding governmentally owned organizations. Out of 500 large organizations in Sweden, the top 25 most innovative companies have been ranked based upon over 7,000 printed press articles from 2018 available through Retriever Media. The companies are ranked by their innovations score which is calculated by the number of articles a company is mentioned in, adjusted to the company size, and multiplied with the mean sentiment score. The top 25 companies from the ranking was compared with 25 reference companies, active within the same industry based on the Swedish Standard Industrial Classification (SNI) number, that received a lower innovation score. Good innovation management practices were analyzed based on 14 qualitative interviews in 12 of the top 15 ranked companies and a quantitative survey responded by 20 top ranked and 17 reference companies. The interviews were semi structured with open ended questions to identify used practices, and the reasoning behind them. Spearman’s correlation method has been used to investigate if there was any correlation between the company’s innovation score, the mean performance score, and the mean importance score rated by respondents. The company case studies provide authentic examples on how and when different methods and concepts are used within industry. However, while theoretical frameworks often are strictly defined and described in solitary, the interviews have shown that when used within industry, it is rather the opposite. In many of the interviewed companies, frameworks and methods are modified, combined and constantly evolving. Aspects that the interviewees have expressed as important for an innovative company are: Innovation and change should be iterative, decentralized and started in small scale while receiving full support from top management. Examples of identified practices are: The innovation vision is used in the decision-making process for new ideas. Keywords connected to innovation are used for guiding new aspirations. There is an overall aim to become industry or/and digital leaders. Although the interviewed companies had similar innovation management practices, they were usually modified to fit within the company’s own organization and industry. The interviews contributed with interesting collection of practices within their authentic setting from which other companies could draw inspiration from. Lastly, a handbook was created describing how to conduct the innovation ranking annually, including a description of how to use the software as well as the required script of code. / Det övergripande syftet med denna uppsats har varit att identifiera och analysera hur ett antal stora och framgångsrika bolag bedriver innovationsledning. Av 500 svenska företag har de 25 mest innovativa rankats baserat på hur företagen framställts i över 7000 tryckta artiklar under 2018. I artiklarna som tagits fram via Retriever Media har företagen poängsatts efter antalet artiklar som de omnämnts i, korrigerat efter företagens storlek, multiplicerat med artiklarnas genomsnittliga sentimentvärde. De 25 högst rankade företagen jämfördes sedan med 25 referensföretag aktiva inom samma bransch enligt standarden för svensk näringsindelning (SNI). God innovationsledningspraxis identifierades och analyserades genom 14 intervjuer med 12 av de 15 högst rankade företagen, samt en enkätstudie som besvarades av 20 av de 25 högst rankade företagen och 17 av referensbolagen. Intervjuerna var semi strukturerade med öppna frågor för att identifiera den innovationsledningspraxis som företagen använder sig av samt bakomliggande resonemang. Spearmans rangkorrelation användes för att identifiera eventuella korrelationer mellan företagens innovationsrankning och hur företaget presterar med avseende på olika innovationsaspekter samt hur viktiga dessa aspekter anses. Analysen av innovationsledningspraxis resulterade i praktiska exempel på hur och när olika metoder, verktyg och strategier användes inom företagen. Managementteorier som kan uppfattas som strikta i litteraturen visade sig kombineras, modifieras och utvecklas i flera av de intervjuade företagen. Aspekter som företagen lyfte fram som viktiga var att innovation och förändring behöver ske iterativt, decentraliseras och startas småskaligt med full uppbackning av företagsledningen. Några av de olika sätt att framgångsrikt leda innovation som identifierats är att: Det finns en vision för hur för företaget ska jobba med innovation och denna vision ligger till grund för mycket av den beslutsfattande processen när det kommer till nya idéer. Nyckelord kopplade till olika innovationsmål används frekvent för att leda forskning och utveckling i rätt riktning. Det finns även ett övergripande mål om att bli det ledande företaget inom olika områden och näringsgrenar. Även om många av de intervjuade företagen hade liknande innovationsledningspraxis så var denna ofta modifierade för att passa det enskilda bolaget eller branschen. De intervjuade företagen bidrog med en stor mängd intressanta metoder och insikter som andra företag kan inspireras och dra nytta av för att förbättra sin innovationsledningsförmåga. Slutligen sammanställdes en handbok för att genomföra en innovationsrankning, inklusive hur man använder de programvaror som krävs samt all nödvändig kod för att möjliggöra en återkommande rankning av innovativa företag.