Página 1 dos resultados de 47 itens digitais encontrados em 0.004 segundos

Classification of opinionated texts by analogy

Pais, Sebastião
Fonte: Universidade da Beira Interior Publicador: Universidade da Beira Interior
Tipo: Dissertação de Mestrado
Publicado em //2008 ENG
Relevância na Pesquisa
46.44%
With the disproportionate increase of theWorldWideWeb and the quantity of information services and their availability, we have an excessive accumulation of documents of various kinds. Despite the positive aspects this represents and the potential this causes, a new problem arises as we need capable tools and methodologies to classify a document as to its quality. Assessing the quality of a Web page is not easy. For the technical evaluation of the structure of Web pages, many are the works that have emerged. This thesis follows a different course. It seeks to evaluate the content of pages according to the opinions and feelings they highlight. The adopted basis criterion to assess the quality ofWeb pages is to examine the absence of opinions and feelings in the texts. When we consult information from the Web, how do we know exactly that the information is reliable and does not express opinions which are made available to the public feelings? How can we ensure when we read a text that we are not being misled by the author who is expressing his opinion or, once again, his feelings? How can we ensure that our own assessment is free from any judgment of value that we can defend? Because of these questions, the area of "Opinion Mining"...

Enriching semantic knowledge bases for opinion mining in big data applications

Weichselbraun, A.; Gindl, S.; Scharl, A.
Fonte: Elsevier Publicador: Elsevier
Tipo: Artigo de Revista Científica
Publicado em /10/2014 EN
Relevância na Pesquisa
46.07%
This paper presents a novel method for contextualizing and enriching large semantic knowledge bases for opinion mining with a focus on Web intelligence platforms and other high-throughput big data applications. The method is not only applicable to traditional sentiment lexicons, but also to more comprehensive, multi-dimensional affective resources such as SenticNet. It comprises the following steps: (i) identify ambiguous sentiment terms, (ii) provide context information extracted from a domain-specific training corpus, and (iii) ground this contextual information to structured background knowledge sources such as ConceptNet and WordNet. A quantitative evaluation shows a significant improvement when using an enriched version of SenticNet for polarity classification. Crowdsourced gold standard data in conjunction with a qualitative evaluation sheds light on the strengths and weaknesses of the concept grounding, and on the quality of the enrichment process.

Máquina de aprendizado extremo aplicada à análise de sentimentos

Fonte: Universidade Federal de Lavras Publicador: Universidade Federal de Lavras
Tipo: Trabalho de Conclusão de Curso
PT_BR
Relevância na Pesquisa
46.17%
The instantaneous increase the amount of information (and opinions) available on the World Wide Web (Internet), leverages the need for the creation and improvement of methods and tools able to exploit the opinational and emotional contents published, diary, by a growing amount of users. Computational Intelligence techniques have been used in wide Data Mining applications. Out of numerous Artificial Intelligence techniques, Artificial Neural Networks and Support Vector Machines (SVMs) have been played the leading roles. However, it is known that both, Neural Networks and SVMs, face some challenging and troubles issues such as: slowness learning speed, not trivial human intervention and/or poor computational scalability. Extreme Learning Machine (ELM), an emergent method to training Neural Networks, arrives to overcome some of this challenges faced by other techniques. ELM works for Single-Hidden Layer Feedforward Networks (SLFNs) and its essence is that the hidden layer of SLFNs doesn’t need to be tuned. When compared with the traditional computational intelligence techniques, ELM provides better generalization performance at a much faster learning speed without requiring human intervention. This study intends to evaluate these and other features of the recent ELM in order to perform a quantitative and qualitative analysis. The intention is to conduct a comparative between the proposed method and the SVM...

Protótipo para mineração de opinião em redes sociais: estudo de casos selecionados usando o twitter

Fonte: Universidade Federal de Lavras Publicador: Universidade Federal de Lavras
Tipo: Trabalho de Conclusão de Curso
PT_BR
Relevância na Pesquisa
46.36%
This work aimed the development of a prototype that is able to perform opinion mining in texts from social networks, using Twitter as a study case. A detailed description of the concepts associated with the field of web mining and the process of text mining was presented, showing the current techniques for its realization. The programming language Java was used to build the prototype, but previously, a small UML modeling was done. The machine learning method known as SVM was chosen to perform the binary classification between positive and negative sentiments, which represents an action of opinion mining or sentiment analysis. To represent the text documents in a structured manner, it was opted to use the feature vector, which is a statistical approach to text analysis. In the tests executed, it was possible to observe that the trained classifier achieved an average accuracy of 80% on the desired classifications. It was concluded that success was obtained with the prototype created, because it was able to perform the tasks solicited in a reasonable way.

Sistema de clasificación automática de críticas de cine

Martín García, Miriam
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: info:eu-repo/semantics/bachelorThesis; info:eu-repo/semantics/masterThesis Formato: application/pdf
SPA
Relevância na Pesquisa
36.37%
Considerada inicialmente una subdisciplina de la tarea de clasificación de documentos, en los últimos años la clasificación de documentos basada en la opinión (conocida en inglés bajo los nombres de sentiment classification, sentiment analysis u opinion mining) ha sido objeto de un creciente interés por parte de la comunidad de investigadores del procesamiento del lenguaje natural. El creciente interés por el procesamiento automático de las opiniones contenidas en documentos de texto, es en parte consecuencia del aumento exponencial de contenidos generados por usuarios en la Web 2.0, y por el interés, entre otros, de empresas y administraciones públicas en analizar, filtrar o detectar automáticamente las opiniones vertidas por sus clientes o ciudadanos. Este Proyecto de Fin de Carrera tiene como objetivo el diseño y la implementación de un sistema de clasificación automática de textos de opinión, concretamente de críticas cinematográficas vertidas por usuarios de internet, recogidas en diferentes webs dedicadas a tal fin. Los documentos serán clasificados, en una de las categorías definidas en el sistema (de acuerdo a la orientación afectiva de las críticas), aplicando diversas técnicas para el procesamiento del lenguaje natural (se aplicará en un caso el algoritmo kNN y en otro caso se hará uso de un diccionario afectivo). El hecho de conseguir un sistema automático de clasificación evitará la intervención humana y aumentará la rapidez con que se pueden procesar este tipo de documentos. Con la realización de este proyecto...

Minería de opiniones basada en características guiada por ontología

Peñalver Martínez, Isidro
Fonte: Universidade de Múrcia Publicador: Universidade de Múrcia
Tipo: Tese de Doutorado Formato: application/pdf
SPA
Relevância na Pesquisa
36.45%
OBJETIVOS El trabajo realizado en esta tesis doctoral persigue los siguientes objetivos: (i) Definición y formalización de una metodología de minería de opiniones basada en características para clasificar los sentimientos de las opiniones. Esta metodología incluirá procesamiento del lenguaje natural, identificación de características, cálculo de la polaridad de las características y análisis de sentimientos; (ii) Diseño e implementación de una aplicación software para llevar a cabo el proceso de análisis de sentimientos de las opiniones de los usuarios. Este sistema se diseñará para cumplir con los requisitos que implica el entorno de minería de opiniones descrito. Se emplearán para ello las tecnologías más novedosas y los recursos mejor valorados disponibles actualmente; (iii) Validación de la aplicación de software en varios dominios. La metodología propuesta y el software desarrollado serán validados en dos dominios totalmente diferentes: opiniones sobre películas y finanzas. METODOLOGÍA La metodología que se ha creado responde a un innovador sistema de análisis de sentimientos basado en características que utiliza como base de conocimiento una ontología del dominio. Esta metodología propuesta es independiente del dominio y del idioma empleados. A partir de ella se identifican las características relevantes dentro de cada opinión. Durante el proceso de identificación se tiene en cuenta la estructura semántica de la ontología. Cada una de las frases que contengan expresiones lingüísticas que estén directamente relacionadas con términos de la ontología se tienen en cuenta para calcular la polaridad global de la opinión del usuario. La aplicación de esta metodología ha propiciado el desarrollo de un nuevo software para la clasificación de sentimientos de opiniones basado en cálculos vectoriales en el espacio R3. CONCLUSIONES El tipo de lenguaje informal que emplean los usuarios en sus opiniones dificulta mucho el empleo de técnicas de PLN efectivas. Las herramientas que tenemos en la actualidad no contemplan irregularidades lingüísticas en la mayoría de los casos. La investigación llevada a cabo en este trabajo ha estado motivada principalmente por la carencia de recursos...

Classification of opinionated texts by analogy

Pais, Sebastião
Fonte: Universidade da Beira Interior Publicador: Universidade da Beira Interior
Tipo: Dissertação de Mestrado
Publicado em //2008 ENG
Relevância na Pesquisa
46.44%
With the disproportionate increase of theWorldWideWeb and the quantity of information services and their availability, we have an excessive accumulation of documents of various kinds. Despite the positive aspects this represents and the potential this causes, a new problem arises as we need capable tools and methodologies to classify a document as to its quality. Assessing the quality of a Web page is not easy. For the technical evaluation of the structure of Web pages, many are the works that have emerged. This thesis follows a different course. It seeks to evaluate the content of pages according to the opinions and feelings they highlight. The adopted basis criterion to assess the quality ofWeb pages is to examine the absence of opinions and feelings in the texts. When we consult information from the Web, how do we know exactly that the information is reliable and does not express opinions which are made available to the public feelings? How can we ensure when we read a text that we are not being misled by the author who is expressing his opinion or, once again, his feelings? How can we ensure that our own assessment is free from any judgment of value that we can defend? Because of these questions, the area of "Opinion Mining"...

A novel deterministic approach for aspect-based opinion mining in tourism products reviews

Velásquez, Juan D.; Bravo Marquez, Felipe; Marrese Taylor, Edison
Fonte: Elsevier Publicador: Elsevier
Tipo: Artículo de revista
EN
Relevância na Pesquisa
46.22%
Articulo de publicacion SCOPUS; This work proposes an extension of Bing Liu’s aspect-based opinion mining approach in order to apply it to the tourism domain. The extension concerns with the fact that users refer differently to different kinds of products when writing reviews on the Web. Since Liu’s approach is focused on physical product reviews, it could not be directly applied to the tourism domain, which presents features that are not considered by the model. Through a detailed study of on-line tourism product reviews, we found these features and then model them in our extension, proposing the use of new and more complex NLP-based rules for the tasks of subjective and sentiment classification at the aspect-level. We also entail the task of opinion visualization and summarization and propose new methods to help users digest the vast availability of opinions in an easy manner. Our work also included the development of a generic architecture for an aspect-based opinion mining tool, which we then used to create a prototype and analyze opinions from TripAdvisor in the context of the tourism industry in Los Lagos, a Chilean administrative region also known as the Lake District. Results prove that our extension is able to perform better than Liu’s model in the tourism domain...

Diseño e implementación de una aplicación de web opinion mining para identificar preferencias de usuarios sobre productos turísticos de la X región de Los Lagos

Marrese Taylor, Edison
Fonte: Universidad de Chile Publicador: Universidad de Chile
Tipo: Tesis
EN
Relevância na Pesquisa
66.57%
Ingeniero Civil Industrial; El objetivo de este trabajo es diseñar e implementar una aplicación de web opinion mining para encontrar preferencias sobre productos turísticos en la X Región de Los Lagos, Chile. Esta aplicación se desarrolló bajo el proyecto FONDEF D10I1198, conocido como WHALE (Web Hypermedia Analysis Long-Term Environment), que aborda la situación de la industria del turismo en Los Lagos, donde los operadores turísticos caracterizan la demanda y definen la oferta usando estudios de alcance limitado. Estos estudios no son capaces de cubrir un número representativo de participantes porque se aplican a grupos específicos de personas, dejando la demanda potencial proveniente de fuera de la región sin estudiar. Dada esta situación, se torna importante considerar métodos alternativos de estudio. Con el explosivo crecimiento de la Web 2.0, la cantidad de información disponible on-line es hoy inmensa. Este trabajo ofrece un enfoque que considera una nueva alternativa para descubrir preferencias de clientes sobre productos turísticos, particularmente hoteles y restaurants, usando opiniones disponibles en la Web en la forma de reviews. Esta tarea presenta desafíos importantes, principalmente por el hecho de que los datos son variables en el tiempo y están frecuentemente dispuestos en una forma semi-estructurada. En este contexto...

Extracción de información y conocimiento de las opiniones emitidas por usuarios de los sistemas WEB 2.0

Dueñas Fernández, Rodrigo Alfonso
Fonte: Universidad de Chile Publicador: Universidad de Chile
Tipo: Tesis
ES
Relevância na Pesquisa
56.26%
Magíster en Gestión de Operaciones; Ingeniero Civil Industrial; El objetivo de este trabajo de tesis es desarrollar una plataforma informática Web Opinion Mining (WOM) para la extracción de información que permita caracterizar la demanda de productos y servicios de una empresa, a través del uso de documentos publicados en sitios de noticias y las opiniones consignadas por los usuarios de las redes sociales. En la sociedad de hoy, gracias a la aparición de la Web, el panorama competitivo de las empresas se ha vuelto mucho más complejo, debido a la cantidad de mercados interconectados en tiempo real que tienen que considerar. Por lo tanto, para obtener rendimientos sobre el promedio en este medio, es necesario tener nuevas maneras de predecir las acciones de la competencia y la demanda por productos y servicios. Debido a lo anterior, la necesidad de procesar grandes cantidades de datos para obtener información ha ido creciendo a lo largo de los años. A medida que la capacidad de una empresa de procesar los datos de su entorno aumenta y se vuelve capaz de tomar decisiones estratégicas en base a la información obtenida, obtiene ventajas competitivas que reditúan en rendimientos sobre el promedio. En base a lo anterior, es que se plantea la siguiente hipótesis de investigación: Las opiniones de los usuarios sobre productos y servicios de un nicho de mercado particular consignadas en los sistemas Web 2.0...

Diseño e implementación de un sistema para la clasificación de tweets según su polaridad

Tapia Caro, Pablo Andrés
Fonte: Universidad de Chile Publicador: Universidad de Chile
Tipo: Tesis
ES
Relevância na Pesquisa
45.94%
Ingeniero Civil Indusrial; La alta penetración de Twitter en Chile ha favorecido que esta red social sea utilizada por empresas, políticos y organizaciones como un medio para obtener información adicional de las opiniones de usuarios acerca de sus productos, servicios o ellos mismos. Al ser los comentarios en Twitter, por defecto, de carácter público, se pueden analizar con el fin de extraer información accionable. En particular las empresas además de estar interesadas en la información cuantitativa, les interesa saber bajo qué polaridad se efectúan estas menciones, por cuanto una variación positiva en el número de comentarios puede deberse a un mayor número de menciones tanto positivas como negativas. Si bien existen un número considerable de softwares que vienen con la funcionalidad de detección de polaridad de sentimientos, estos no son de mucha utilidad ya que la forma en que interactúa el usuario chileno con esta plataforma está llena de modismos propios de nuestro lenguaje local y abreviaciones que se deben principalmente a la limitación de caracteres de Twitter. Al ser esta una industria inmadura en Chile, la tarea de detección de polaridad de sentimientos, se está realizando de forma manual por agencias publicitarias y otro tipo de empresas...

Identificación de las tendencias de reclamos presentes en reclamos.cl y que apunten contra instituciones de educación y organizaciones públicas

Beth Madariaga, Daniel Guillermo
Fonte: Universidad de Chile Publicador: Universidad de Chile
Tipo: Tesis
ES
Relevância na Pesquisa
66.28%
Ingeniero Civil Industrial; En la siguiente memoria se busca corroborar, por medio de una experiencia práctica y aplicada, si a caso el uso de las técnicas de Web Opinion Mining (WOM) y de herramientas informáticas, permiten determinar las tendencias generales que pueden poseer un conjunto de opiniones presentes en la Web. Particularmente, los reclamos publicados en el sitio web Reclamos.cl, y que apuntan contra instituciones pertenecientes a las industrias nacionales de Educación y de Gobierno. En ese sentido, los consumidores cada vez están utilizando más la Web para publicar en ella las apreciaciones positivas y negativas que poseen sobre lo que adquieren en el mercado, situación que hace de esta una mina de oro para diversas instituciones, especialmente para lo que es el identificar las fortalezas y las debilidades de los productos y los servicios que ofrecen, su imagen pública, entre varios otros aspectos. Concretamente, el experimento se realiza a través de la confección y la ejecución de una aplicación informática que integra e implementa conceptos de WOM, tales como Knowledge Discovery from Data (KDD), a modo de marco metodológico para alcanzar el objetivo planteado, y Latent Dirichlet Allocation (LDA), para lo que es la detección de tópicos dentro de los contenidos de los reclamos abordados. También se hace uso de programación orientada a objetos...

Opinion Mining and Analysis: A survey

Buche, Arti; Chandak, Dr. M. B.; Zadgaonkar, Akshay
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/07/2013
Relevância na Pesquisa
46.29%
The current research is focusing on the area of Opinion Mining also called as sentiment analysis due to sheer volume of opinion rich web resources such as discussion forums, review sites and blogs are available in digital form. One important problem in sentiment analysis of product reviews is to produce summary of opinions based on product features. We have surveyed and analyzed in this paper, various techniques that have been developed for the key tasks of opinion mining. We have provided an overall picture of what is involved in developing a software system for opinion mining on the basis of our survey and analysis.; Comment: 10 pages

Opinion Mining In Hindi Language: A Survey

Sharma, Richa; Nigam, Shweta; Jain, Rekha
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/04/2014
Relevância na Pesquisa
46.54%
Opinions are very important in the life of human beings. These Opinions helped the humans to carry out the decisions. As the impact of the Web is increasing day by day, Web documents can be seen as a new source of opinion for human beings. Web contains a huge amount of information generated by the users through blogs, forum entries, and social networking websites and so on To analyze this large amount of information it is required to develop a method that automatically classifies the information available on the Web. This domain is called Sentiment Analysis and Opinion Mining. Opinion Mining or Sentiment Analysis is a natural language processing task that mine information from various text forms such as reviews, news, and blogs and classify them on the basis of their polarity as positive, negative or neutral. But, from the last few years, enormous increase has been seen in Hindi language on the Web. Research in opinion mining mostly carried out in English language but it is very important to perform the opinion mining in Hindi language also as large amount of information in Hindi is also available on the Web. This paper gives an overview of the work that has been done Hindi language.

Subjectivity Classification using Machine Learning Techniques for Mining Feature-Opinion Pairs from Web Opinion Sources

Kamal, Ahmad
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 25/12/2013
Relevância na Pesquisa
46.47%
Due to flourish of the Web 2.0, web opinion sources are rapidly emerging containing precious information useful for both customers and manufactures. Recently, feature based opinion mining techniques are gaining momentum in which customer reviews are processed automatically for mining product features and user opinions expressed over them. However, customer reviews may contain both opinionated and factual sentences. Distillations of factual contents improve mining performance by preventing noisy and irrelevant extraction. In this paper, combination of both supervised machine learning and rule-based approaches are proposed for mining feasible feature-opinion pairs from subjective review sentences. In the first phase of the proposed approach, a supervised machine learning technique is applied for classifying subjective and objective sentences from customer reviews. In the next phase, a rule based method is implemented which applies linguistic and semantic analysis of texts to mine feasible feature-opinion pairs from subjective sentences retained after the first phase. The effectiveness of the proposed methods is established through experimentation over customer reviews on different electronic products.; Comment: 10 pages, 2 Color Photographs...

Opinion mining of movie reviews at document level

Sharma, Richa; Nigam, Shweta; Jain, Rekha
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/08/2014
Relevância na Pesquisa
46.32%
The whole world is changed rapidly and using the current technologies Internet becomes an essential need for everyone. Web is used in every field. Most of the people use web for a common purpose like online shopping, chatting etc. During an online shopping large number of reviews/opinions are given by the users that reflect whether the product is good or bad. These reviews need to be explored, analyse and organized for better decision making. Opinion Mining is a natural language processing task that deals with finding orientation of opinion in a piece of text with respect to a topic. In this paper a document based opinion mining system is proposed that classify the documents as positive, negative and neutral. Negation is also handled in the proposed system. Experimental results using reviews of movies show the effectiveness of the system.; Comment: International Journal on Information Theory (IJIT), Vol.3, No.3, July 2014

Sentiment Analysis Using Collaborated Opinion Mining

Virmani, Deepali; Malhotra, Vikrant; Tyagi, Ridhi
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 12/01/2014
Relevância na Pesquisa
46.24%
Opinion mining and Sentiment analysis have emerged as a field of study since the widespread of World Wide Web and internet. Opinion refers to extraction of those lines or phrase in the raw and huge data which express an opinion. Sentiment analysis on the other hand identifies the polarity of the opinion being extracted. In this paper we propose the sentiment analysis in collaboration with opinion extraction, summarization, and tracking the records of the students. The paper modifies the existing algorithm in order to obtain the collaborated opinion about the students. The resultant opinion is represented as very high, high, moderate, low and very low. The paper is based on a case study where teachers give their remarks about the students and by applying the proposed sentiment analysis algorithm the opinion is extracted and represented.; Comment: 5 pages, 6 figures

Mining of product reviews at aspect level

Sharma, Richa; Nigam, Shweta; Jain, Rekha
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 14/06/2014
Relevância na Pesquisa
36.38%
Todays world is a world of Internet, almost all work can be done with the help of it, from simple mobile phone recharge to biggest business deals can be done with the help of this technology. People spent their most of the times on surfing on the Web it becomes a new source of entertainment, education, communication, shopping etc. Users not only use these websites but also give their feedback and suggestions that will be useful for other users. In this way a large amount of reviews of users are collected on the Web that needs to be explored, analyse and organized for better decision making. Opinion Mining or Sentiment Analysis is a Natural Language Processing and Information Extraction task that identifies the users views or opinions explained in the form of positive, negative or neutral comments and quotes underlying the text. Aspect based opinion mining is one of the level of Opinion mining that determines the aspect of the given reviews and classify the review for each feature. In this paper an aspect based opinion mining system is proposed to classify the reviews as positive, negative and neutral for each feature. Negation is also handled in the proposed system. Experimental results using reviews of products show the effectiveness of the system.

Opinion mining of text documents written in Macedonian language

Gajduk, Andrej; Kocarev, Ljupco
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/11/2014
Relevância na Pesquisa
46.13%
The ability to extract public opinion from web portals such as review sites, social networks and blogs will enable companies and individuals to form a view, an attitude and make decisions without having to do lengthy and costly researches and surveys. In this paper machine learning techniques are used for determining the polarity of forum posts on kajgana which are written in Macedonian language. The posts are classified as being positive, negative or neutral. We test different feature metrics and classifiers and provide detailed evaluation of their participation in improving the overall performance on a manually generated dataset. By achieving 92% accuracy, we show that the performance of systems for automated opinion mining is comparable to a human evaluator, thus making it a viable option for text data analysis. Finally, we present a few statistics derived from the forum posts using the developed system.; Comment: In press, MASA proceedings

A POS Tagger for Social Media Texts Trained on Web Comments

Neunerdt,Melanie; Reyer,Michael; Mathar,Rudolf
Fonte: Instituto Politécnico Nacional, Centro de Innovación y Desarrollo Tecnológico en Cómputo Publicador: Instituto Politécnico Nacional, Centro de Innovación y Desarrollo Tecnológico en Cómputo
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/12/2013 EN
Relevância na Pesquisa
45.94%
Using social media tools such as blogs and forums have become more and more popular in recent years. Hence, a huge collection of social media texts from different communities is available for accessing user opinions, e.g., for marketing studies or acceptance research. Typically, methods from Natural Language Processing are applied to social media texts to automatically recognize user opinions. A fundamental component of the linguistic pipeline in Natural Language Processing is Part-of-Speech tagging. Most state-of-the-art Part-of-Speech taggers are trained on newspaper corpora, which differ in many ways from non-standardized social media text. Hence, applying common taggers to such texts results in performance degradation. In this paper, we present extensions to a basic Markov model tagger for the annotation of social media texts. Considering the German standard Stuttgart/Tübinger TagSet (STTS), we distinguish 54 tag classes. Applying our approach improves the tagging accuracy for social media texts considerably, when we train our model on a combination of annotated texts from newspapers and Web comments.