Listing 1 - 10 of 13 | << page >> |
Sort by
|
Choose an application
Doelstelling: De voornaamste doelstelling van dit onderzoek bestaat erin om na te gaan of het mogelijk is om Nederlandstalige online consumentenbeoordelingen automatisch te classificeren volgens subjectiviteit. Deze subjectiviteit wordt uitgedrukt in 5 klassen: zeer negatief, negatief, neutraal, positief en zeer positief. De consumentenbeoordelingen zijn verdeeld over verschillende domeinen waarvoor de consument het vaakst het internet raadpleegt alvorens tot aankoop over te gaan. Het uiteindelijke doel is het systeem toe te passen op nieuwe, ongeziene consumentenbeoordelingen en de accuraatheid ervan te meten. Anderzijds wordt de toepasbaarheid gemeten van domeinspecifieke lexicons naar andere domeinen. Middelen of methode: De gebruikte methode is lexicongebaseerde automatische sentiment mining waarbij op zoek gegaan wordt naar de subjectiviteit van taaluitingen, in dit geval consumentenbeoordelingen. Als basis voor het onderzoek werd een corpus van 500 Nederlandstalige reviews samengesteld, verdeeld over 5 domeinen: elektronica, films, auto's, hotels en cd's. Deze reviews zijn handmatig beoordeeld op hun subjectiviteit en verdeeld over 5 klassen. Tevens werden alle subjectieve woorden in de beoordelingen geannoteerd en ingedeeld in 4 klassen: zeer negatieve, negatieve, positieve en zeer positieve woorden. Deze woorden zijn per domein opgelijst in een sentimentlexicon. Daarnaast werd ook gebruik gemaakt van een bestaand sentimentlexicon voor het Nederlands, opgesteld door Jijkoun. Aan de hand van een zelfgemaakt programma, het samengestelde corpus en de lexicons zijn de 5 domeinen geanalyseerd op hun accuraatheid, precisie, recall en F-score. Resultaten: Voor dit onderzoek werden verschillende experimenten uitgevoerd met alle mogelijke combinaties van beschikbare hulpmiddelen. Over het algemeen zijn de verkregen resultaten unaniem: alleen een lexicongebaseerd systeem voor consumentenbeoordelingen volstaat niet om zeer gedetailleerde resultaten te generen. De beste resultaten zijn echter wel verkregen bij zeer uitgebreide lexicons die domeinafhankelijk zijn. Op basis van onze experimentele resultaten concluderen we bijgevolg dat er vooral twee factoren een grote rol spelen in het slagen van lexicongebaseerde systemen: de grootte van het lexicon en de domeinafhankelijkheid van een lexicon.
Consumentenbeoordeling. --- Domeinadaptatie. --- Domeinafhankelijk lexicon. --- Lexicon gebaseerd. --- Nederlandstalig. --- Online meningen. --- Opinion mining. --- Review. --- Sentimentanalyse. --- Subjectiviteit. --- Taaltechnologische studie.
Choose an application
The desire to know if stock markets are predictable has long attracted the interest of academic research and businesses. The first works on the subject were based on two well-known theories: random walk theory and the efficient market hypothesis (EMH). Although these theories suggest that news is not used to determine market prices, researchers are trying to demonstrate their usefulness and impact on the different variables. The purpose of this analysis is to determine whether there is a correlation between the feelings of financial tweets and stock prices. The litterature has shown a correlation between forum activity, stock volatility and trading volume. We have been able to prove the correlation using a Vector Autoregression Model.
Choose an application
Doelstellingen: In deze masterproef wordt onderzocht of bedrijven afhankelijk zijn van hun online imago en hoe ze dit imago proberen te bewaken. Daarbij komen de volgende deelvragen aan bod: zijn bedrijven actief op sociale media en passen ze met tools sentiment analyse toe om een inzicht te krijgen in de zogenaamde Web 2.0 content? Een uitgebreide literatuurstudie van het domein van de sentiment analyse en een verkennende marktstudie laten toe om een eventuele kloof te ontdekken tussen de verwachtingen van bedrijven omtrent deze technologie en de mogelijkheden die de huidige tools bieden. Middelen of methode: Aan de hand van een grondige literatuurstudie wordt eerst de status quaestionis in het onderzoeksdomein samengevat. Na deze wetenschappelijke bespreking volgt een kritische analyse van een aantal tools en applicaties zodat de lezer ook een inzicht krijgt in de praktische toepassingen van sentiment analyse. Aan de hand van een marktstudie wordt ten slotte nagegaan of bedrijven actief zijn op sociale media en of ze sentiment analyse tools ook effectief gebruiken om hun online imago te bewaken. Als doelgroep werd gekozen om te werken met Vlaamse media en web shops. Resultaten: Uit de resultaten van de marktstudie blijkt dat alle respondenten, 7 uit de Vlaamse media en 8 uit web shops, actief zijn op ten minste één sociaal netwerk. Daarnaast stelden we vast dat de eigenlijke content op deze netwerken bij beide doelgroepen, i.e. 90%, al een deel uitmaakt van de online marktstrategie.Toch zien we dat slechts 1 op 15 respondenten sentiment analyse toepast om een meer gedetailleerd beeld te verkrijgen van wat er online over het bedrijf wordt verspreid. Deze kloof tussen de activiteit op sociale media en de integratie van sentiment analyse tools, wijst erop dat dit medium nog niet optimaal geïntegreerd is in de bedrijfsstrategie. Als we deze bevinding plaatsen naast de grote wetenschappelijke ontwikkelingen in het veld en het veelvuldig verschijnen van nieuwe tools kunnen we stellen dat we ons op een keerpunt bevinden. Deze studie is dan ook een goed vertrekpunt voor bedrijven die wensen hun online marktstrategie verder uit te bouwen of voor ontwikkelaars van sentiment analyse tools om nieuwe inzichten te verkrijgen in de markt.
Machine learning. --- Marketing Strategy. --- Opinion Mining Tools. --- Sentiment Analysis. --- Social Media. --- Taaltechnologische studie. --- User-generated Content. --- Web 2.0.
Choose an application
Sentiment analysis --- Machine learning --- Analysis, Sentiment --- Extraction, Opinion --- Mining, Opinion --- Mining, Sentiment --- Opinion extraction --- Opinion mining --- Sentiment mining --- Computational linguistics --- Data mining
Choose an application
Sentiment analysis has gained widespread adoption in many fields, but not-until now-in literary studies. Scholars have lacked a robust methodology that adapts the tool to the skills and questions central to literary scholars. Also lacking has been quantitative data to help the scholar choose between the many models. Which model is best for which narrative, and why? By comparing over three dozen models, including the latest Deep Learning AI, the author details how to choose the correct model-or set of models-depending on the unique affective fingerprint of a narrative. The author also demonstrates how to combine a clustered close reading of textual cruxes in order to interpret a narrative. By analyzing a diverse and cross-cultural range of texts in a series of case studies, the Element highlights new insights into the many shapes of stories.
Criticism --- Sentiment analysis. --- Data processing. --- Analysis, Sentiment --- Extraction, Opinion --- Mining, Opinion --- Mining, Sentiment --- Opinion extraction --- Opinion mining --- Sentiment mining --- Computational linguistics --- Data mining --- Evaluation of literature --- Literary criticism --- Literature --- Rhetoric --- Aesthetics --- Technique --- Evaluation
Choose an application
Sentiment analysis has gained widespread adoption in many fields, but not-until now-in literary studies. Scholars have lacked a robust methodology that adapts the tool to the skills and questions central to literary scholars. Also lacking has been quantitative data to help the scholar choose between the many models. Which model is best for which narrative, and why? By comparing over three dozen models, including the latest Deep Learning AI, the author details how to choose the correct model-or set of models-depending on the unique affective fingerprint of a narrative. The author also demonstrates how to combine a clustered close reading of textual cruxes in order to interpret a narrative. By analyzing a diverse and cross-cultural range of texts in a series of case studies, the Element highlights new insights into the many shapes of stories.
Criticism --- Sentiment analysis --- Computational linguistics --- Data mining --- Analysis, Sentiment --- Extraction, Opinion --- Mining, Opinion --- Mining, Sentiment --- Opinion extraction --- Opinion mining --- Sentiment mining --- Literature --- Rhetoric --- Aesthetics --- Evaluation of literature --- Literary criticism --- Data processing --- Technique --- Evaluation
Choose an application
Opinion mining is a prevalent research issue in many domains. In the financial domain, however, it is still in the early stages. Most of the researches on this topic only focus on the coarse-grained market sentiment analysis, i.e., 2-way classification for bullish/bearish. Thanks to the recent financial technology (FinTech) development, some interdisciplinary researchers start to involve in the in-depth analysis of investors' opinions. These works indicate the trend toward fine-grained opinion mining in the financial domain. When expressing opinions in finance, terms like bullish/bearish often spring to mind. However, the market sentiment of the financial instrument is just one type of opinion in the financial industry. Like other industries such as manufacturing and textiles, the financial industry also has a large number of products. Financial services are also a major business for many financial companies, especially in the context of the recent FinTech trend. For instance, many commercial banks focus on loans and credit cards. Although there are a variety of issues that could be explored in the financial domain, most researchers in the AI and NLP communities only focus on the market sentiment of the stock or foreign exchange. This open access book addresses several research issues that can broaden the research topics in the AI community. It also provides an overview of the status quo in fine-grained financial opinion mining to offer insights into the futures goals. For a better understanding of the past and the current research, it also discusses the components of financial opinions one-by-one with the related works and highlights some possible research avenues, providing a research agenda with both micro- and macro-views toward financial opinions.
Natural language & machine translation --- Data mining --- Algorithms & data structures --- Artificial intelligence --- Information technology: general issues --- Natural Language Processing (NLP) --- Data Mining and Knowledge Discovery --- Data Structures and Information Theory --- Artificial Intelligence --- Computer Applications --- Data Science --- Computer and Information Systems Applications --- Open Access --- financial opinion mining --- text mining in finance --- financial technology application --- FinTech --- argument mining in finance --- opinion quality evaluation --- numeral understanding --- Expert systems / knowledge-based systems --- Information theory
Choose an application
This Element provides a basic introduction to sentiment analysis, aimed at helping students and professionals in corpus linguistics to understand what sentiment analysis is, how it is conducted, and where it can be applied. It begins with a definition of sentiment analysis and a discussion of the domains where sentiment analysis is conducted and used the most. Then, it introduces two main methods that are commonly used in sentiment analysis known as "supervised machine-learning" and "unsupervised learning (or lexicon-based)" methods, followed by a step-by-step explanation about how to perform sentiment analysis with R. The Element then provides two detailed examples or cases of sentiment and emotion analysis, with one using an unsupervised method and the other using a supervised learning method.
Natural language processing (Computer science) --- Computational linguistics. --- Sentiment analysis. --- Analysis, Sentiment --- Extraction, Opinion --- Mining, Opinion --- Mining, Sentiment --- Opinion extraction --- Opinion mining --- Sentiment mining --- Computational linguistics --- Data mining --- Automatic language processing --- Language and languages --- Language data processing --- Linguistics --- Natural language processing (Linguistics) --- Applied linguistics --- Cross-language information retrieval --- Mathematical linguistics --- Multilingual computing --- NLP (Computer science) --- Artificial intelligence --- Electronic data processing --- Human-computer interaction --- Semantic computing --- Data processing
Choose an application
Sentiment analysis is a branch of natural language processing concerned with the study of the intensity of the emotions expressed in a piece of text. The automated analysis of the multitude of messages delivered through social media is one of the hottest research fields, both in academy and in industry, due to its extremely high potential applicability in many different domains. This Special Issue describes both technological contributions to the field, mostly based on deep learning techniques, and specific applications in areas like health insurance, gender classification, recommender systems, and cyber aggression detection.
opinion mining --- affect computing --- health insurance --- Twitter --- hybrid vectorization --- violence against women --- word association --- collaborative schemes of sentiment analysis and sentiment systems --- random forest --- cyber-aggression --- deep learning --- online review --- emotion analysis --- lexicon construction --- provider networks --- text mining --- sentiment lexicon --- social media --- sentiment-aware word embedding --- psychographic segmentation --- medical web forum --- gender classification --- racism --- sentiment analysis --- sentiment classification --- sentiment word analysis --- social networks --- convolutional neural network --- review data mining --- machine learning --- emotion classification --- big data-driven marketing --- text feature representation --- recommender system --- user preference prediction --- violence based on sexual orientation --- semantic networks
Choose an application
This book presents diverse contributions related to some of the latest advances in the field of personalization and recommender systems, as well as social media and sentiment analysis. The work comprises several articles that address different problems in these areas by means of recent techniques such as deep learning, methods to analyze the structure and the dynamics of social networks, and modern language processing approaches for sentiment analysis, among others. The proposals included in the book are representative of some highly topical research directions and cover different application domains where they have been validated. These go from the recommendation of hotels, movies, music, documents, or pharmacy cross-selling to sentiment analysis in the field of telemedicine and opinion mining on news, also including the study of social capital on social media and dynamics aspects of the Twitter social network.
History of engineering & technology --- music recommender systems --- social influence --- social trust --- homophily --- collaborative filtering --- streaming services --- ego network --- events --- network dynamics --- Twitter --- hybrid recommender systems --- feedback collection --- digital libraries --- information retrieval --- real-world data --- open-access --- social capital --- social media --- operationalization --- measurement --- scoping review --- graph convolutional neural network --- recommender system --- cross-sales --- pharmacy --- popularity bias --- opinion mining --- opinion summarization --- topic modeling --- semantic similarity measures --- word embeddings --- text mining --- sentiment analysis --- Web-based questionnaire --- telemedicine --- telemonitoring --- telehomecare --- recommender systems --- utility --- multi-criteria --- penalty --- over-expectation --- under-expectation --- n/a
Listing 1 - 10 of 13 | << page >> |
Sort by
|