PERBANDINGAN ALGORITMA KLASIFIKASI SUPPORT VECTOR MACHINE DAN NAIVE BAYES PADA IMBALANCE DATA

Question classification is a computer science system, which aims to analyze questions and can label each question based on existing categories. Questions can be collected from several materials or topics that are many and different. Therefore, the researcher intends to create a classification system for quiz questions Data Warehouse and Business Intelligence which can be grouped into topics Data Warehouse, Business Intelligence, Data Analytics, and Performance Measurement. One way to solve this problem is by approach machine learning. In this study, researchers used a comparison of machine learning algorithms, namely the algorithm NaïveBayes and SupportVectorMachine using SMOTE and methods Cross-Validation The results of this study show the best accuracy results and are very helpful. The results obtained in the method cross-validation before SMOTE resulted in an accuracy rate of 82.02% for the results after going through the SMOTE stage of 94.79% on the algorithm Naïve Bayes, while the algorithm SupportVectorMachine get accuracy of 81.39% in the process before SMOTE for the results after going through SMOTE of 96.52%. Keywords: Cross-Validation; Machine Learning; Naive Bayes; Support Vector Machine; Question Classification Abstrak: Klasifikasi pertanyaan merupakan sebuah sistem ilmu komputer, yang bertujuan untuk menganalisis pertanyaan serta dapat memberi label pada setiap pertanyaan berdasarkan kategori yang ada. Pertanyaan soal dapat dikumpulkan dari beberapa materi atau topik yang banyak dan berbeda. Oleh karena itu, bermaksud untuk membuat sistem klasifikasi pertanyaan soal kuis Data Warehouse dan Business Intelligence yang dapat dikelompokkan menjadi topik Data Warehouse, Business Intelligence, Data Analitik, dan Pengukuran Kinerja. Cara yang dapat dilakukan untuk permasalahan ini dengan menggunakan pendekatan MachineLearning. Pada penelitian kali ini menggunakan perbandingan algoritma MachineLearning yaitu algoritma NaïveBayes dan SupportVectorMachine menggunakan metode SMOTE dan Cross-Validation. Hasil penelitian ini menunjukkan hasil akurasi yang terbaik dan sangat membantu. Hasil yang diperoleh pada metode cross-validation sebelum SMOTE menghasilkan tingkat akurasi sebesar 82.02% untuk hasil sesudah melalui tahap SMOTE sebesar 94.79 % pada algoritma Naïve Bayes, sedangkan pada algoritma Support Vector Machine menghasilkan akurasi sebesar pada proses sebelum SMOTE 81.39% untuk hasil sesudah melalui SMOTE sebesar 96.52%. Kata kunci: Klasifikasi Pertanyaan; Pembelajaran Mesin; Naive Bayes; Support Vector Machine; Cross-Validation

The Research of Convolutional Neural Network Based on Integrated Classification in Question Classification

As a new generation of search engine, automatic question answering system (QAS) is becoming more and more important and has become one of the hotspots of computer application research and natural language processing (NLP). However, as an indispensable part of the QAS, the role of question classification is an understood thing in the system. In view of this, to further make the performance of question classification much better, both the feature extraction and the classification model were explored. On the study of existing CNN research, an improved CNN model based on Bagging integrated classification (“W2V + B-CNN” for short) is proposed and applied to question classification. Firstly, we combine the characteristics of short texts, use the Word2Vec tool to map the features of the words to a certain dimension, and organize the question sentences into the form of a two-dimensional matrix similar to the image. Then, the trained word vectors are used as the input of the CNN for feature extraction. Finally, the Bagging integrated classification algorithm is used to replace the Softmax classification of the traditional CNN for classification. In other words, the good of W2V + B-CNN model is that it can make use of the advantages of CNN and Bagging integrated classification at the same time. Overall, the new model can not only use the powerful feature extraction capabilities of CNN to extract the potential features of natural language questions but also use the good data classification capabilities of the integrated classification algorithm for feature classification at the same time, which can help improve the accuracy of the W2V + B-CNN in the application of question classification. The comparative experiment results prove that the effect of the W2V + B-CNN is significantly better than that of the CNN and other classification algorithms in question classification.

A comparative analysis on question classification task based on deep learning approaches

Question classification is one of the essential tasks for automatic question answering implementation in natural language processing (NLP). Recently, there have been several text-mining issues such as text classification, document categorization, web mining, sentiment analysis, and spam filtering that have been successfully achieved by deep learning approaches. In this study, we illustrated and investigated our work on certain deep learning approaches for question classification tasks in an extremely inflected Turkish language. In this study, we trained and tested the deep learning architectures on the questions dataset in Turkish. In addition to this, we used three main deep learning approaches (Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN)) and we also applied two different deep learning combinations of CNN-GRU and CNN-LSTM architectures. Furthermore, we applied the Word2vec technique with both skip-gram and CBOW methods for word embedding with various vector sizes on a large corpus composed of user questions. By comparing analysis, we conducted an experiment on deep learning architectures based on test and 10-cross fold validation accuracy. Experiment results were obtained to illustrate the effectiveness of various Word2vec techniques that have a considerable impact on the accuracy rate using different deep learning approaches. We attained an accuracy of 93.7% by using these techniques on the question dataset.