Combining Classification and Clustering for Tweet Sentiment Analysis

Coletta, Luiz Fernando Sommaggio; Silva, Nádia Félix Felipe da; Hruschka, Eduardo R.; Hruschka, Estevam R.

doi:10.1109/bracis.2014.46

Cited by 64 publications

(30 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One recent research demonstrated combining classification and clustering algorithms for Tweet Sentiment Analysis using an SVM classifier along with a clustering ensemble to achieve better classification accuracies by espousing a C3E-SL algorithm which refines tweet classifications from additional information provided by clusterers [12].…”

Section: Related Workmentioning

confidence: 99%

Augmented Machine Learning Ensemble Extension Model for Social Media Health Trends Predictions

2019

ijrte

View full text Add to dashboard Cite

Social Networks are the source of rich, interactive, textual, and other media.Users of the social media generate data at a tremendous pace.This data consisting of user opinions and attitudes is so large that it has necessitated automated methods to analyze and extract knowledge from the same. Social networks have been studied and analyzed using various graph-based analysis techniques. Prominent analysishas centered on features like ego-networks, distance, centrality, sub-networks etc. The areas of study for social media analysis have been centered around populations, boundaries, Cohesion, Centrality and Brokerage, Prestige and Ranking. In the past several models have been propounded for various machine learning based analytics for the Social Networks study but there is a perceived need for studying social networks for health data using Ensemble Learning wherein an array of various Machine Learning techniques can be employed to achieve better classification or clustering results. We introduce an Analytical Model which will identify most discussed terms/ topics of health/ healthcare on social networks to predict the emerging health trends. The model is to use temporal datasets to deduce multi-label classification of health-related topics. The Model employs the technique of Temporal Clustering (using Machine Learning) on the Topic Classification done on datasets using Ensemble Machine Learning to deduce the most discussed topics. Using this model, we will see how Ensemble Machine Learning based Analytical Model for analyzing social network data for health topics is efficient than traditional Machine Learning technique(s).

show abstract

Section: Related Workmentioning

confidence: 99%

Augmented Machine Learning Ensemble Extension Model for Social Media Health Trends Predictions

2019

ijrte

View full text Add to dashboard Cite

show abstract

“…O próximo capítulo aborda os principais conceitos sobre meta-heurísticas de busca, as quais são particularmente adequadas para o problema de otimização paramétrica (e.g., otimização de parâmetros em métodos de aprendizado de máquina). Este estudo resultou na concepção de um novo algoritmo evolutivo, o qual tem sido usado para a calibração automática do algoritmo C 3 E-SL (COLETTA et al, 2015a;COLETTA et al, 2014).…”

Section: Considerações Finaisunclassified

“…A abordagem semissupervisionada proposta aqui estende o estudo de Coletta et al (2014), no qual a combinação de classificadores e agrupadores foi usada para classificar tweets de maneira supervisionada. Esta extensão, descrita a partir da Seção 4.1, utiliza o algoritmo C 3 E-SL para combinar máquinas de vetores de suporte (Support Vector Machines -SVMs (CORTES; VAPNIK, 1995; BOSER; GUYON; VAPNIK, 1992)) com a informação de similaridades entre tweets de um conjunto alvo que se deseja classificar.…”

Section: Aprendizado Semissupervisionado Combinando Classificadores Eunclassified

“…O algoritmo C 3 E-SL, conforme abordado na Seção 2.1.2, recebe distribuições de probabilidades de classes que serão refinadas em um processo de otimização. Tipicamente, estas distribuições são resultantes de uma agregação de classificadores (COLETTA et al, 2015b;COLETTA et al, 2014;ACHARYA et al, 2014;ACHARYA et al, 2011), mas o uso de um único classificador operando de maneira independente também é possível. Mais detalhadamente, a versão semissupervisionada do C 3 E-SL refina resultados de um classificador SVM.…”

Section: E-sl Semissupervisionadounclassified

“…Além das distribuições de probabilidades de classes para objetos de um conjunto alvo, o C 3 E-SL requer também uma matriz de similaridades construída a partir deste conjunto. Em (ACHARYA et al, 2014;ACHARYA et al, 2011;COLETTA et al, 2014) esta matriz provém de agregadores de agrupadores. Já na versão semissupervisionada do algoritmo, a matriz é obtida diretamente dos dados brutos seguindo os três passos a seguir:…”

Section: E-sl Semissupervisionadounclassified

See 2 more Smart Citations

Abordagens para combinar classificadores e agrupadores em problemas de classificação

Coletta¹

Self Cite

View full text Add to dashboard Cite

show abstract

Multimodal sentimental analysis for social media applications: A comprehensive review

Chandrasekaran

Nguyen

Hemanth

2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text-based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve humanmachine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.

show abstract

Combining Classification and Clustering for Tweet Sentiment Analysis

Cited by 64 publications

References 36 publications

Augmented Machine Learning Ensemble Extension Model for Social Media Health Trends Predictions

Augmented Machine Learning Ensemble Extension Model for Social Media Health Trends Predictions

Abordagens para combinar classificadores e agrupadores em problemas de classificação

Multimodal sentimental analysis for social media applications: A comprehensive review

Contact Info

Product

Resources

About