A Comparative Study of Selected Classifiers with Classification Accuracy in User Profiling

Cufoglu, Ayse; Lohi, Mahi; Madani, Kambiz

doi:10.1109/csie.2009.954

Cited by 26 publications

(21 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 shows that NB outperforms BN and J48 classifiers with respect to the accuracy and mean absolute error of classification of BoTySeGa gameplay data. Our result confirms the previous result [23,24] …”

Section: A the Classification Resultssupporting

confidence: 83%

Intelligent Classification of Learner's Cognitive Domain using Bayes Net, Naïve Bayes, and J48 Utilizing Bloom's Taxonomy-based Serious Game

Sukajaya

Purnama

Purnomo

2015

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Abstract-Lately, personalized learning approach attracted the attention of so many researchers due to its capacity to improve the quality of educational system. This approach provides opportunities to maximize the potential of all students based on their profile. This indicates the necessity of grouping learners! ! profiles appropriately in order to optimize contribution of personalized learning approach in achieving learning objective. The problems occurred when classifying learners! ! profile especially when dealing with large number of learners, restricted time to classify, and requirement of authentic data. To solve the problem, we proposed the implementation of Bloom! !s taxonomy-based serious game as an assessment tool replacing paper-based tool for the gameplay data collection. Three different methods namely: BN, NB, and J48 were implemented to obtain the highest accuracy of classification. Our study finds that the NB classifier gives the highest percentage accuracy that is 92.31%. This classifier has the similar accuracy with BN but with lower error rate. In view of the strength of agreement, the result is categorized Very Good (" " = 0.85).

show abstract

Section: A the Classification Resultssupporting

confidence: 83%

Intelligent Classification of Learner's Cognitive Domain using Bayes Net, Naïve Bayes, and J48 Utilizing Bloom's Taxonomy-based Serious Game

Sukajaya

Purnama

Purnomo

2015

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

show abstract

“…Moreover, Locally Weighted Learning (LWL), RepTree, Decision Table and SVMReg classifiers were compared for classification. Previous works [44], [45], [46] and [47] have been the first in the literature to present the comparison of the classification and clustering accuracy performance of different algorithms with user profiles. In [45] NB, Instance Based Learner (IBL), Bayesian Network (BN) and Lazy Bayesian Rules (LBR) classifiers were compared using a user profile dataset.…”

Section: Classification and Clustering Algorithms For User Profilingmentioning

confidence: 99%

“…In [45] NB, Instance Based Learner (IBL), Bayesian Network (BN) and Lazy Bayesian Rules (LBR) classifiers were compared using a user profile dataset. Furthermore in [46], Decision Tree (DT) algorithms to be used for user profiling (i.e. Classification and Regression Tree (SimpleCART), NBTree, Id3, J48 -a version of C4.5-and Sequential Minimal Optimization (SMO)) were included and compared with large user profile data.…”

Section: Classification and Clustering Algorithms For User Profilingmentioning

confidence: 99%

User Profiling - A Short Review

Cufoglu¹

2014

IJCA

Self Cite

View full text Add to dashboard Cite

In Today's technology driven world user profiles are the virtual representation of each user and they include a variety of user information such as personal, interest and preference data. These profiles are the outcome of the user profiling process and they are essential to service personalization. Different methods, techniques and algorithms have been proposed in the literature for the user profiling process. This paper aims to give an overview on the user profiling and its related concepts, and discuss the pros and cons of current methods for the future service personalization. Furthermore, it also give details about the simulations which have been carried out with well known classification and clustering algorithms with real world user profile dataset. This work is based on the doctoral thesis of the author.

show abstract

“…ID3 is one of the popular DT algorithms that deal with nominal data sets, does not deal with missing values [16]. ID3 is the classical version of the decision tree induction and its improved versions are; SPRINT, SLIQ, and CART.…”

Section: Introductionmentioning

confidence: 99%

“…The researchers mentioned the weaknesses points of DT; it has high error rates when the training set contains a small number of instances of a large variety of different classes, DT algorithm may not work well on data sets when attribute split in any other shape exist. Decision Trees are automatically quite expensive to build.ID3 is one of the popular DT algorithms that deal with nominal data sets, does not deal with missing values [16]. ID3 is the classical version of the decision tree induction and its improved versions are; SPRINT, SLIQ, and CART.…”

mentioning

confidence: 99%

An Experimental Study of Classification Algorithms for Terrorism Prediction

Tolan¹,

Soliman²

2015

IJKE

View full text Add to dashboard Cite

Abstract-Terrorist attacks are the biggest challenging problem for the mankind across the world, which need the wholly attention of the researchers, practitioners to cope up deliberately. To predict the terrorist group which is responsible of attacks and activities using historical data is a complicated task due to the lake of detailed terrorist data. This research based on predicting terrorist groups responsible of attacks in Egypt from year 1970 up to 2013 by using data mining classification technique to compare five base classifiers namely; Naïve Bayes (NB), K-Nearest Neighbour (KNN), Tree Induction (C4.5), Iterative Dichotomiser (ID3), and Support Vector Machine (SVM) depend on real data represented by Global terrorism Database (GTD) from National Consortium for the study of terrorism and Responses of Terrorism (START). The goal of this research is to present two different approaches to handle the missing data as well as provide a detailed comparative study of the used classification algorithms and evaluate the obtained results via two different test options. Experiments are performed on real-life data with the help of WEKA and the final evaluation and conclusion based on four performance measures which showed that SVM, is more accurate than NB and KNN in mode imputation approach, ID3 has the lowest classification accuracy although it performs well in other measures, and in Litwise deletion approach; KNN outperformed the other classifiers in its accuracy, but the overall performance of SVM is acceptable than other classifiers.Index Terms-KDD, precision, recall, terrorist group. I. INTRODUCTIONTerrorist attacks are biggest, challenging, and leading issue in the whole world. It is one of the central points of concentration in all governments. Data mining is popularly known as Knowledge Discovery in Databases (KDD), it is a logical process of discovering new patterns from large data sets involving methods combined with statistics, database systems, support vector machine, artificial intelligence, meta-heuristics, and machine learning. The main goal of data mining is to extract useful, hidden predictive knowledge from large data sets in a human understandable structure and involves database, data management and pre-processing tools, model and interface capabilities, post-processing of discovered structure, visualization and online updating methods for finding hidden patterns, and predictive information that expert may miss because it lies outside their expectations [1], [2]. Data mining and automated data analysis techniques have become used as effective branch of the most important key features for many applications, data mining has a wide number of applications ranging from marketing and advertising of goods, services or products, artificial intelligence research, biological sciences, crime investigations to high-level government intelligence [3]. Recently there has been much concern on using data mining in detecting and investigating unusual patterns, crimes, terrorist activities and preventing the fraudulent...

show abstract

A Comparative Study of Selected Classifiers with Classification Accuracy in User Profiling

Cited by 26 publications

References 6 publications

Intelligent Classification of Learner's Cognitive Domain using Bayes Net, Naïve Bayes, and J48 Utilizing Bloom's Taxonomy-based Serious Game

Intelligent Classification of Learner's Cognitive Domain using Bayes Net, Naïve Bayes, and J48 Utilizing Bloom's Taxonomy-based Serious Game

User Profiling - A Short Review

An Experimental Study of Classification Algorithms for Terrorism Prediction

Contact Info

Product

Resources

About