Random Forest and Support Vector Machine based Hybrid Approach to Sentiment Analysis

Al-Amrani, Yassine; Lazaar, Mohamed; Kadiri, Kamal Eddine El

doi:10.1016/j.procs.2018.01.150

Cited by 213 publications

(111 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It calculates a maximum margin hyperplane which divides the data points into two classes. In text classification, Support Vector Machine is considered the best classification algorithm [31], [32]. SVM algorithm generally divides the training dataset into minimum of two classes.…”

Section: B Phase II Using Machine Learning Methodsmentioning

confidence: 99%

Sentiment Analysis of Facebook Posts using Hybrid Method

Sinha¹,

Saxena²,

Joshi³

2019

IJRTE

View full text Add to dashboard Cite

 Abstract: Social Media is a popular medium of communication amongst youngsters to remain connected with their friends. Facebook is one of the most preferred Social Media Sites which store the gigantic amount of data which can be explored for Sentiment Analysis. In this study, we have applied hybrid analysis approach which combines the best features of a lexical analysis and SVM machine learning classification algorithm on Facebook Posts. The analysis is further improved by incorporating language discourse features to detect intensity of sentiment and the prominent emotions expressed through these posts.

show abstract

Section: B Phase II Using Machine Learning Methodsmentioning

confidence: 99%

Sentiment Analysis of Facebook Posts using Hybrid Method

Sinha¹,

Saxena²,

Joshi³

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…(3) both algorithms were applied in the past to perform NLP [30]; and (4) decision-trees and SVM were included among the 25 best classifiers identified in a deep analysis performed in [31].…”

Section: Statistical Modelsmentioning

confidence: 99%

Evaluating Information-Retrieval Models and Machine-Learning Classifiers for Measuring the Social Perception towards Infectious Diseases

et al. 2019

View full text Add to dashboard Cite

Recent outbreaks of infectious diseases remind us the importance of early-detection systems improvement. Infodemiology is a novel research field that analyzes online information regarding public health that aims to complement traditional surveillance methods. However, the large volume of information requires the development of algorithms that handle natural language efficiently. In the bibliography, it is possible to find different techniques to carry out these infodemiology studies. However, as far as our knowledge, there are no comprehensive studies that compare the accuracy of these techniques. Consequently, we conducted an infodemiology-based study to extract positive or negative utterances related to infectious diseases so that future syndromic surveillance systems can be improved. The contribution of this paper is two-fold. On the one hand, we use Twitter to compile and label a balanced corpus of infectious diseases with 6164 utterances written in Spanish and collected from Central America. On the other hand, we compare two statistical-models: word-grams and char-grams. The experimentation involved the analysis of different gram sizes, different partitions of the corpus, and two machine-learning classifiers: Random-Forest and Sequential Minimal Optimization. The results reach a 90.80% of accuracy applying the char-grams model with five-char-gram sequences. As a final contribution, the compiled corpus is released.

show abstract

“…Yassine et al, [11] used amazon dataset that resulted from the product comments for Sentiment analysis. They proposed supervised learning algorithms like Support Vector Machine, Random Forest and Random Forest Support Vector Machine algorithms (RFSVM) for generating rules in classification technique.…”

Section: Related Workmentioning

confidence: 99%

“…Outfit Bagging produces a precision of 83% and booting calculation, for example, Adaboost, Gradient boosting and XGB boosting produces an exactness of 84%, 86% and 86 % respectively. The fundamental variation between various boosting calculations is that their strategy for weighting preparing information focuses and theories [11] [12]. Stacking strategy delivers an exactness of 84 %.…”

Section: Fig 2: Accuracy Of Various Classification Techniquesmentioning

confidence: 99%

Behavior Prophecy of Stock Trader using Machine Learning Techniques

Gowda¹,

Lakshmikantha²

2019

IJITEE

View full text Add to dashboard Cite

 Abstract: The web utilization by users is expanding very rapidly. Users are getting to data and administrations effectively through different media like social correspondence, sight and sound substance, web based trading, banking administrations and so forth. It winds up provoking undertaking to precisely recognize and separate typical and suspicious human behavior conduct. Every unique application need to predict user behavior to forecast and upgrade their administration quality. This work gives the examination of stock trader conduct recognition and expectation. Many Machine Learning (ML) methods and recognizable proof strategies are looked at and examined for stock trader behavior analysis. Their parameters are considered and enhancements are recommended. The proposed procedure portrays stock trader conduct discovery framework. The vital segment examination is the classification and prediction technique used to recognize and understand the typical and irregular behavior of the stock trader.

show abstract

Random Forest and Support Vector Machine based Hybrid Approach to Sentiment Analysis

Cited by 213 publications

References 9 publications

Sentiment Analysis of Facebook Posts using Hybrid Method

Sentiment Analysis of Facebook Posts using Hybrid Method

Evaluating Information-Retrieval Models and Machine-Learning Classifiers for Measuring the Social Perception towards Infectious Diseases

Behavior Prophecy of Stock Trader using Machine Learning Techniques

Contact Info

Product

Resources

About