UWB at SemEval-2016 Task 5: Aspect Based Sentiment Analysis

Hercig, Tomáš; Brychcín, Tomáš; Svoboda, Lukás̆; Konkol, Michal

doi:10.18653/v1/s16-1055

Cited by 48 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The extension of LDA with modified LDA has been proposed in [36]. The sentiment analysis by using the machine learning, rule based, Lexicon based and deep learning was proposed in [40][41][42][43][44][45][46][47].…”

Section: Related Workmentioning

confidence: 99%

Classification of Social Media Users Based on Disagreement and Stance Analysis

Riaz

Minhas

Bibi³

et al. 2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

Analyzing conversational behavior is a primary task in the field of sentiment analysis. Different researchers have proposed their models to perform the sentiment analysis of social media discussions. Existing approaches mainly studying the conversational behavior based on the text in the conversation. In any discussion, the users could have different viewpoints about the topic of conversation. A user can agree or disagree on the topic of discussion. Agreement of a user to the topic is called a stance, and if the user disagrees to the topic, we refer it as disagreement. The classification of the users based on stance and disagreement is not a well-researched area, and need to be explored further. In this work, we have proposed a computational model to classify the members according to stance or disagreement. The proposed model uses the novel approach, and it is a hybrid of topic modeling and VADER (Valence Aware Dictionary and sEntiment Reasoner). To evaluate the proposed model, we have conducted an experiment, and we did use the WhatsApp group discussion, Facebook comments as a dataset. We also compared the proposed model with two baseline approach, topic modeling, and VADER. From the results, we can conclude that the proposed model can effectively classify social media users based on disagreement and stance. Keywords: Opinion mining Á Sentiment analysis Á Stance analysis Á Topic modeling Á LDA Á VADER

show abstract

Section: Related Workmentioning

confidence: 99%

Classification of Social Media Users Based on Disagreement and Stance Analysis

Riaz

Minhas

Bibi³

et al. 2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…En [3], los autores describen el sistema que utilizan en la tarea 5 de SemEval 2016. Su sistema se basa en aprendizaje automático supervisado, utilizando un clasificador de máxima entropía, campo aleatorio condicional, y un gran número de características tales como vectores globales, la asignación de Dirichlet latente, bolsa de palabras, iconos gestuales y otros.…”

Section: Trabajo Relacionadosunclassified

“…Función utilizada en scikit-learn http://scikit-learn.org/ 3. Convierte una colección de documentos sin formato a una matriz de características TF-IDF.…”

unclassified

Un algoritmo para detectar la polaridad de opiniones en los dominios de laptops y restaurantes

Vazquez¹,

Tovar²,

Vilariño³

et al. 2016

RCS

View full text Add to dashboard Cite

Resumen. En este artículo se presenta un estudio para la detección de Polaridad en un conjunto de opiniones de usuarios emitidos hacia Restaurantes en el idioma español e inglés, asi como para opiniones escritas a valoraciones de Laptops en el idioma inglés. Como solución propuesta se emplea Máquina de Soporte Vectorial con validación cruzada. Los mejores resultados se presentaron para el Dominio de Restaurantes en español con un 74% de precisión.Palabras clave: Minería de opiniones, aprendizaje supervisado, procesamiento de lenguaje natural.Abstract. In this article, we present a study for the detection of polarity over a dataset of opinions of users over Restaurants in the Spanish and English language, as well as, opinions about Laptops in the English language. As a proposed solution, we use Vector Support Machine with cross validation. The best results were presented for the Spanish Restaurant Domain with 74% accuracy.

show abstract

“…In [4], authors describe the system they used in the task 5 of SemEval 2016. Their system is based on supervised machine learning, using a Maximum Entropy classifier, conditional random fields, and a large number of features such as global vectors, Latent Dirichlet Allocation, bag of words, emoticons, and others.…”

Section: Related Workmentioning

confidence: 99%

A Lexical Supervised Approach for Opinion Mining in the Domain of Laptops and Restaurants

Vazquez¹,

Tovar²,

Pinto³

et al. 2016

RCS

View full text Add to dashboard Cite

This paper presents a study of opinion mining or sentiment analysis for detection of polarity in a set of users opinion about restaurants written in Spanish and English. The research work is performed with the aim of solving a task proposed in SemEval 2016, thus we employed the same dataset proposed in that evaluation conference. The proposed approach uses a vector model for representing the information, including lexical features such as the following ones: word unigrams, bigrams and trigrams. The obtained results show a performance up to 71% when using word unigrams for representing the opinions written in English in the domain of restaurants.

show abstract

UWB at SemEval-2016 Task 5: Aspect Based Sentiment Analysis

Cited by 48 publications

References 23 publications

Classification of Social Media Users Based on Disagreement and Stance Analysis

Classification of Social Media Users Based on Disagreement and Stance Analysis

Un algoritmo para detectar la polaridad de opiniones en los dominios de laptops y restaurantes

A Lexical Supervised Approach for Opinion Mining in the Domain of Laptops and Restaurants

Contact Info

Product

Resources

About