Simultaneous clustering and classification over cluster structure representation

Qian, Qiang; Chen, Songcan; Cai, Weiling

doi:10.1016/j.patcog.2011.11.027

Cited by 20 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To take advantage of both labeled and unlabeled data, several researches have designed ways of combining classifiers and clusterers [22], [37], [38], [39], [40], [41], [21], [42], [43]. Acharya et al [21] and Gao et al [43], in particular, deal with the combination of a handful of classifiers and clusterers with the ultimate goal of classifying new data.…”

Section: Related Workmentioning

confidence: 99%

Combining Classification and Clustering for Tweet Sentiment Analysis

Coletta

Silva

Hruschka

et al. 2014

2014 Brazilian Conference on Intelligent Systems

View full text Add to dashboard Cite

Abstract-The goal of sentiment analysis is to determine opinions, emotions, and attitudes presented in source material. In tweet sentiment analysis, opinions in messages can be typically categorized as positive or negative. To classify them, researchers have been using traditional classifiers like Naive Bayes, Maximum Entropy, and Support Vector Machines (SVM). In this paper, we show that a SVM classifier combined with a cluster ensemble can offer better classification accuracies than a stand-alone SVM. In our study, we employed an algorithm, named C 3 E-SL, capable to combine classifier and cluster ensembles. This algorithm can refine tweet classifications from additional information provided by clusterers, assuming that similar instances from the same clusters are more likely to share the same class label. The resulting classifier has shown to be competitive with the best results found so far in the literature, thereby suggesting that the studied approach is promising for tweet sentiment classification.

show abstract

Section: Related Workmentioning

confidence: 99%

Combining Classification and Clustering for Tweet Sentiment Analysis

Coletta

Silva

Hruschka

et al. 2014

2014 Brazilian Conference on Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…In particularly, clustering is used: (1) to create a training set from the unlabelled set [15], (2) to augment an existing labeled set with new documents from the unlabeled data set [11], (3) to augment the data set with new features [8,16], and (4) to co-train a classifier [17,18]. More recently, simultaneous learning frameworks for clustering and classification have been proposed [19,20].…”

Section: Related Workmentioning

confidence: 99%

Clustering based two-stage text classification requiring minimal training data

Zhang

Xiao

2012

2012 International Conference on Systems and Informatics (ICSAI2012)

View full text Add to dashboard Cite

Clustering has been employed to expand training data in some semi-supervised learning methods. Clustering based methods are based on the assumption that the learned clusters under the guidance of initial training data can somewhat characterize the underlying distribution of the data set. However, our experiments show that whether such assumption holds is based on both the separability of the considered data set and the size of the training data set. It is often violated on data set of bad separability, especially when the initial training data are too few. In this case, clustering based methods would perform worse. In this paper, we propose a clustering based two-stage text classification approach to address the above problem. In the first stage, labeled and unlabeled data are first clustered with the guidance of the labeled data. Then a self-training style clustering strategy is used to iteratively expand the training data under the guidance of an oracle or expert. At the second stage, discriminative classifiers can subsequently be trained with the expanded labeled data set. Unlike other clustering based methods, the proposed clustering strategy can effectively cope with data of bad separability. Furthermore, our proposed framework converts the challenging problem of sparsely labeled text classification into a supervised one, therefore, supervised classification models, e.g. SVM, can be applied, and techniques proposed for supervised learning can be used to further improve the classification accuracy, such as feature selection, sampling methods and data editing or noise filtering. Our experimental results demonstrated the effectiveness of our proposed approach especially when the size of the training data set is very small.

show abstract

“…Classification is a supervised learning approach which is a significant field of research that involved labeling an object to one of a group of classes, related to features of that object and it is considered one of the basic difficulties in a lot of decision making processes [1]- [8]. Many decision-making processes are examples of classification difficulty that can be simply transformed into classification difficulty, e.g., prognosis processes, diagnosis processes, and pattern recognition [9].…”

Section: Introductionmentioning

confidence: 99%

Solving Support Vector Machine Model Selection Problem Using Continuous Ant Colony Optimization

Alwan¹,

Ku-Mahamud²

2013

IJIPM

View full text Add to dashboard Cite

Ant Colony Optimization has been used to solve Support Vector Machine model selection problem. Ant Colony Optimization originally deals with discrete optimization problem. In applying Ant Colony Optimization for optimizing Support Vector Machine parameters which are continuous variables, there is a need to discretize the continuously value into discrete value. This discretize process would result in loss of some information and hence affect the classification accuracy and seeking time. This study proposes an algorithm that can optimize Support Vector Machine parameters using Continuous Ant Colony Optimization without the need to discretize continuous value for Support Vector Machine parameters. Eight datasets from UCI were used to evaluate the credibility of the proposed hybrid algorithm in terms of classification accuracy and size of features subset. Promising results were obtained when compared to grid search technique, GA with feature chromosome -SVM, PSO-SVM, and GA-SVM.

show abstract

Simultaneous clustering and classification over cluster structure representation

Cited by 20 publications

References 20 publications

Combining Classification and Clustering for Tweet Sentiment Analysis

Combining Classification and Clustering for Tweet Sentiment Analysis

Clustering based two-stage text classification requiring minimal training data

Solving Support Vector Machine Model Selection Problem Using Continuous Ant Colony Optimization

Contact Info

Product

Resources

About