E-commerce product review sentiment classification based on a naïve Bayes continuous learning framework

2020 ◽  
Vol 57 (5) ◽  
pp. 102221 ◽  
Author(s):  
Feng Xu ◽  
Zhenchun Pan ◽  
Rui Xia
Keyword(s):  
Naive Bayes ◽  
Naïve Bayes ◽  
Sentiment Classification ◽  
Continuous Learning ◽  
Product Review ◽  
Learning Framework

Improving Techniques for Naïve Bayes Text Classifiers

2010 ◽  
pp. 111-127
Author(s):  
Han-joon Kim
Keyword(s):  
Text Classification ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Classification Systems ◽  
Classification Model ◽  
Learning Approaches ◽  
Learning Framework ◽  
The Em Algorithm ◽  
Meta Learning ◽  
Text Classifiers

This chapter introduces two practical techniques for improving Naïve Bayes text classifiers that are widely used for text classification. The Naïve Bayes has been evaluated to be a practical text classification algorithm due to its simple classification model, reasonable classification accuracy, and easy update of classification model. Thus, many researchers have a strong incentive to improve the Naïve Bayes by combining it with other meta-learning approaches such as EM (Expectation Maximization) and Boosting. The EM approach is to combine the Naïve Bayes with the EM algorithm and the Boosting approach is to use the Naïve Bayes as a base classifier in the AdaBoost algorithm. For both approaches, a special uncertainty measure fit for Naïve Bayes learning is used. In the Naïve Bayes learning framework, these approaches are expected to be practical solutions to the problem of lack of training documents in text classification systems.

scholarly journals Opinion Mining Classification using Naive Bayes Algorithm

2020 ◽  
Vol 9 (5) ◽  
pp. 495-498
Keyword(s):  
Opinion Mining ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Naive Bayes Classifier ◽  
Bayes Classifier ◽  
Naïve Bayes Classifier ◽  
Product Review ◽  
Online Services ◽  
Recent Advancement ◽  
Bayes Algorithm

With the recent advancement in the field of online services, the importance of a review for a product has also gone up. In this paper we focus on the aspect of reducing the time and effort for the user by recommending the best product to him. For this to be achieved, this paper proposes a Naive Bayes Classifier which labels the reviews accurately and combines the reviews to give a final rating to the product. The amazon product review data consisting of both negative and positive reviews was used for training and testing purposes. The model’s performance is evaluated, and results are analysed.

Sentiment Classification Using Text Embedding for Thai Teaching Evaluation

2019 ◽  
Vol 886 ◽  
pp. 221-226 ◽  
Author(s):  
Kesinee Boonchuay
Keyword(s):  
Naive Bayes ◽  
Geometric Mean ◽  
Nearest Neighbors ◽  
Naïve Bayes ◽  
Teaching Evaluation ◽  
Sentiment Classification ◽  
Teaching Skills ◽  
K Nearest Neighbors ◽  
Overall Performance ◽  
F Measure

Sentiment classification gains a lot of attention nowadays. For a university, the knowledge obtained from classifying sentiments of student learning in courses is highly valuable, and can be used to help teachers improve their teaching skills. In this research, sentiment classification based on text embedding is applied to enhance the performance of sentiment classification for Thai teaching evaluation. Text embedding techniques considers both syntactic and semantic elements of sentences that can be used to improve the performance of the classification. This research uses two approaches to apply text embedding for classification. The first approach uses fastText classification. According to the results, fastText provides the best overall performance; its highest F-measure was at 0.8212. The second approach constructs text vectors for classification using traditional classifiers. This approach provides better performance over TF-IDF for k-nearest neighbors and naïve Bayes. For naïve Bayes, the second approach yields the best performance of geometric mean at 0.8961. The performance of TF-IDF is better suited to using decision tree than the second approach. The benefit of this research is that it presents the workflow of using text embedding for Thai teaching evaluation to improve the performance of sentiment classification. By using embedding techniques, similarity and analogy tasks of texts are established along with the classification.

scholarly journals Less Sparse Feature Set with Meta Heuristic Weighted Classifier for Tweet Sentiment Classification

2020 ◽  
Vol 9 (3) ◽  
pp. 1328-1334
Keyword(s):  
Naive Bayes ◽  
Hybrid Approach ◽  
Naïve Bayes ◽  
Sentiment Classification ◽  
Bayes Classifier ◽  
Hybrid Approaches ◽  
Machine Leaning ◽  
Feature Weight ◽  
Precision And Accuracy ◽  
Better Than

Twitter using Machine Leaning Techniques has been done. While consideration Bigram, Unigram,. SVM and naïve Bayes classifier which hybrid with PSO and ACO for effective feature weight. In Fig. 4.9 compare all experiment by on graph which shows that SVM_ACO and SVM_PSO better perform than SVM. NB_ACO and NB_PSO perform better than NB but if compare between hybrid approaches then SVM_PSO show 81.80% accuracy,85% precision and 80% recall. IN case of naïve Bayes NB_PSO 76.93% accuracy,76.24 precision and 82.55% recall, so experiments conclude that Naive Bayes improve recall and SVM improve precision and accuracy when use as hybrid approach.

Sign in / Sign up

Export Citation Format

Share Document