A Novel Ensemble Approach for Feature Selection to Improve and Simplify the Sentimental Analysis

Latif, Muhammad; Qamar, Usman

doi:10.1007/978-3-030-22871-2_39

Cited by 5 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Latif et al [20] had explained an ensemble approach for sentimental analysis. Here, they introduced a combination of three kinds of features namely, unigram, lexicon, and phrases.…”

Section: Literature Reviewmentioning

confidence: 99%

An efficient sentiment analysis methodology based on long short-term memory networks

Shobana

Murali

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Sentiment analysis is the process of determining the sentiment polarity (positivity, neutrality or negativity) of the text. As online markets have become more popular over the past decades, online retailers and merchants are asking their buyers to share their opinions about the products they have purchased. As a result, millions of reviews are generated daily, making it difficult to make a good decision about whether a consumer should buy a product. Analyzing these enormous concepts is difficult and time-consuming for product manufacturers. Deep learning is the current research interest in Natural language processing. In the proposed model, Skip-gram architecture is used for better feature extraction of semantic and contextual information of words. LSTM (long short-term memory) is used in the proposed model for understanding complex patterns in textual data. To improve the performance of the LSTM, weight parameters are optimized by the adaptive particle Swarm Optimization algorithm. Extensive experiments were conducted on four datasets proved that our proposed APSO-LSTM model secured higher accuracy over the classical methods such as traditional LSTM, ANN, and SVM. According to simulation results, the proposed model is outperforming other existing models in different metrics.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An efficient sentiment analysis methodology based on long short-term memory networks

Shobana

Murali

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Ensemble classifiers were used by (Latif & Qamar, 2019), to maximize the classification accuracy. Initially, three popular features (a combination of phrase, unigram and lexicon) were introduced.…”

Section: Email Classification Based On Sentiment Analysismentioning

confidence: 99%

Sentiment analysis from email pattern using feature selection algorithm

Srinivasarao

Sharaff

2021

Expert Systems

View full text Add to dashboard Cite

Today number of applications are available on mobile devices and computers for electronic mail (email) conversations. The demand for email communication is increasing day‐by‐day. Therefore the incoming and outgoing messages are also getting increased. However, extracting the sentiments from the emails is now demanding. Therefore in the proposed method, the pattern classification and sentiment clustering are carried out in two phases. Initially, the pattern classification is performed using support vector regression, then the sentiments from such classified patterns are clustered using a unsupervised fuzzy‐model‐based Gaussian clustering algorithm. Finally, the experimental analysis is performed in Python tool. The proposed sentiment clustering from email patterns has attained a better accuracy result of 97.13%, which is found higher than other existing techniques. Along with the parametric analysis, non‐parametric statistical analysis using the Wilcoxon rank‐sum test is also carried out to identify the proposed sentiment analysis architecture's effectiveness.

show abstract

Adaptive particle swarm optimization algorithm based long short-term memory networks for sentiment analysis

Shobana

Murali

2021

IFS

View full text Add to dashboard Cite

Text Sentiment analysis is the process of predicting whether a segment of text has opinionated or objective content and analyzing the polarity of the text’s sentiment. Understanding the needs and behavior of the target customer plays a vital role in the success of the business so the sentiment analysis process would help the marketer to improve the quality of the product as well as a shopper to buy the correct product. Due to its automatic learning capability, deep learning is the current research interest in Natural language processing. Skip-gram architecture is used in the proposed model for better extraction of the semantic relationships as well as contextual information of words. However, the main contribution of this work is Adaptive Particle Swarm Optimization (APSO) algorithm based LSTM for sentiment analysis. LSTM is used in the proposed model for understanding complex patterns in textual data. To improve the performance of the LSTM, weight parameters are enhanced by presenting the Adaptive PSO algorithm. Opposition based learning (OBL) method combined with PSO algorithm becomes the Adaptive Particle Swarm Optimization (APSO) classifier which assists LSTM in selecting optimal weight for the environment in less number of iterations. So APSO - LSTM ‘s ability in adjusting the attributes such as optimal weights and learning rates combined with the good hyper parameter choices leads to improved accuracy and reduces losses. Extensive experiments were conducted on four datasets proved that our proposed APSO-LSTM model secured higher accuracy over the classical methods such as traditional LSTM, ANN, and SVM. According to simulation results, the proposed model is outperforming other existing models.

show abstract

A Novel Ensemble Approach for Feature Selection to Improve and Simplify the Sentimental Analysis

Cited by 5 publications

References 30 publications

An efficient sentiment analysis methodology based on long short-term memory networks

An efficient sentiment analysis methodology based on long short-term memory networks

Sentiment analysis from email pattern using feature selection algorithm

Adaptive particle swarm optimization algorithm based long short-term memory networks for sentiment analysis

Contact Info

Product

Resources

About