Download PDFOpen PDF in browser

Social Media Analysis for Sentiment Classification Using Gradient Boosting Machines

EasyChair Preprint no. 5448

12 pagesDate: May 4, 2021


The Sentiment analysis deals with the emotions of users on social media discussions and reviews. Gradient Boosting Machine has shown improved results significantly on many standard classification benchmarks. This paper illustrates the process of text classification for social media to perform sentiment analysis using machine learning (ML) techniques: Gradient boosting machines (GBM), AdaBoost, and eXtreme GBM (XGBM) for analyzing online reviews. The classifiers are trained on a benchmark dataset and performance is assessed in terms of classifier accuracy. A set of systematic experiments are conducted on a social media dataset extracted from the Kaggle. Experimental results reveal that XGBM outperforms in terms of both training and testing accuracy. Sentiment analysis would provide substantial clues about services and product reviews leading to better marketing strategies for branding the products and maximize the level of customer satisfaction and helping in policy-making decisions.

Keyphrases: feature selection, Machine Learning Techniques, Sentiment Analysis, social media, text mining

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Pradeep Kumar and Abdul Wahid},
  title = {Social Media Analysis for Sentiment Classification Using Gradient Boosting Machines},
  howpublished = {EasyChair Preprint no. 5448},

  year = {EasyChair, 2021}}
Download PDFOpen PDF in browser