Fake Review Detection on Yelp Dataset Using Classification Techniques in Machine Learning

Sihombing, Andre; Fong, A.C.M.

doi:10.1109/ic3i46837.2019.9055644

Cited by 15 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the deep learning methods, some forward-thinking neural networks were utilized to identify the news that falls as fake on social media with 97 percent accuracy [1]. According to the study [10], neural networks perform better in detecting, with an accuracy of 81.92 percent. SVM, on the other hand, has a 91 percent greater accuracy than the Decision Tree, according to [11].…”

Section: Discussionmentioning

confidence: 99%

Higher Classification of Fake Political News Using Decision Tree Algorithm over Random Forest Algorithm

Dinesh

RajendranT

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

The current project aims to model and compare the performance of fake news detectors using machine learning algorithms to recognize fake news connected to political topics with high accuracy. The Decision Tree algorithm and the Random Forest algorithm are two algorithms. The methods were developed and evaluated on a dataset including 44,000 samples. Implemented each algorithm through programs and performed ten iterations with different scales of false feeds and factual feeds classification were identified. The G-power test is around 80% accurate. For detecting false political news, the Decision Tree algorithm had a mean accuracy of 99.6990, and the Random Forest approach had a mean accuracy of 98.6380, according to the trial results. The significance of accuracy is p=0.001, indicating the efficacy of the classifier. This research aims to use a novel strategy for contemporary Machine Learning Classifiers to predict fake political news. The comparison results reveal that the Decision Tree method outperforms the Random Forest technique.

show abstract

Section: Discussionmentioning

confidence: 99%

Higher Classification of Fake Political News Using Decision Tree Algorithm over Random Forest Algorithm

Dinesh

RajendranT

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

show abstract

“…A logistic regression algorithm has been used for an online spammer in [51] and achieves 88.3% accuracy.PU Learning-based classification algorithm [52] has been used to detect deceptive review-based classification done in [53], [54], [55], [56] using sentiment analysis, the behavior of reviewer and their reviewing style, drift detection, and text classification, and SVM algorithm gives better performance. Authors in [57], [58] use semantic analysis techniques using decision tables, information gain, XGBoost Model to identify and remove fake reviews for isolation of genuine and reliable reviews. Similarly, various machine learning algorithms like Ad-aBoost, SVM, Bagging Algorithms [59], [60], Hierarchical Attention Network (HAN), and visual image feature using image captioning and forensic analysis [61] for isolation of fake news from real news articles.…”

Section: Case Study Through Fake Review Analysismentioning

confidence: 99%

Enhancing Data Integrity in Mobile Crowdsensing Environment with Machine Learning and Cost-Benefit Analysis

Sahoo¹,

Pradhan²,

Sethi³

et al. 2023

IJCDS

View full text Add to dashboard Cite

Mobile Crowdsensing (MCS) is a major source of a vast dataset containing heterogeneous types of data collected from various sources and stored in the local or remote server. Proper analysis of MCS data helps in better decision-making. However, MCS data suffers from data integrity issues, such as validity, accuracy, and reliability, that affect decision-making. Therefore, ensuring data integrity in the MCS environment is essential as it is a major source of a huge dataset. The proposed work considers user review data collection and analysis using a mobile application developed for the purpose. To ensure the data integrity, identification of fake and invalid reviews in the dataset need to be determined. This work proposes two approaches to solve data integrity issues. The first approach is to detect and eliminate fake/ invalid reviews from the dataset. The second is to identify the sources of fake/ invalid reviews and block them to protect the dataset from future fake reviews. Machine learning (ML) models are proposed to solve these issues and to ensure data integrity by filtering out fake reviews from real-time data sets. The proposed model uses data fuzzification over a purely mathematical model that categorizes users or customers as honest, suspicious, or malicious and their reviews/ feedback as genuine or fake using ratings provided by the user in the MCS Environment. Using the developed mobile application, user can give feedback about the desired location through various devices, which is stored in a cloud platform. The dataset can be analyzed through a fuzzy logic-based mathematical model followed by an ML algorithm and cost-benefit analysis to detect genuine reviews for maintaining data integrity. Further accuracy of the proposed models is compared with popular ML algorithms such as Naive Bayes (NB), Bayes Net(BN), Support Vector Machine(SVM), Decision Tree(J48), and Random Forest(RF). Initially, it achieves 99.79% of accuracy using the Random Forest algorithm that has been enhanced to 100% using cost-benefit analysis in cross-validation mode.

show abstract

“…However, given the subjective nature of recommendations, ongoing efforts persist in exploring methods to enhance and create a more comprehensive recommendation system. [10,11] The dataset utilized in this project is readily available from the Yelp Challenge at Kaggle. [13] This dataset includes comprehensive information about businesses, users, and their reviews across ten metropolitan areas spanning four countries.…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis Based on Machine Learning Algorithms: A Comprehensive Study

jiang,

Kumar

2024

Preprint

View full text Add to dashboard Cite

The Yelp Dataset comprises data collected from 8,021,122 reviews and 209,393 businesses located in 10 major metropolitan areas. This comprehensive dataset includes multiple aspects related to the businesses. We are interested in assessing the reliability of Yelp's review sentiment algorithm by constructing our own specific sentiment analysis algorithm using data mining and machine learning techniques. The system, based on Natural Language Processing (NLP), generates structured text, followed by the application of machine learning (ML) techniques to classify the text as either a 'good' or 'bad' indicator, used for sentiment prediction. The ML models we utilized here include logistic regression, random forest, k-nearest neighbors, and naive Bayes. Our results demonstrate that three of these models can precisely classify the text and accurately predict sentiment.

show abstract

Fake Review Detection on Yelp Dataset Using Classification Techniques in Machine Learning

Cited by 15 publications

References 3 publications

Higher Classification of Fake Political News Using Decision Tree Algorithm over Random Forest Algorithm

Higher Classification of Fake Political News Using Decision Tree Algorithm over Random Forest Algorithm

Enhancing Data Integrity in Mobile Crowdsensing Environment with Machine Learning and Cost-Benefit Analysis

Sentiment Analysis Based on Machine Learning Algorithms: A Comprehensive Study

Contact Info

Product

Resources

About