Sentiment Analysis of Electronics Product Tweets Using Big Data Framework

Kumar, Sunil; Koolwal, Vartika; Mohbey, Krishna Kumar

doi:10.5455/jjcit.71-1546924503

Cited by 9 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…F1-score: As a general rule, the harmonic mean for Accuracy and Review provides a much better; a significantly better; higher; a stronger and more enhanced gauge than the Precision Metric of the incorrectly categorized occurrences. It is given, mathematically, as: (7) www.ijacsa.thesai.org Accuracy: It is the sum of all the cases in which the predictions were right. It is given as:…”

Section: Results Analysismentioning

confidence: 99%

See 1 more Smart Citation

Analyzing Sentiment in Terms of Online Feedback on Top of Users' Experiences

Alonazi

2023

IJACSA

View full text Add to dashboard Cite

Since most businesses today are conducted online, it is crucial that each customer provide feedback on the various items offered. Evaluating online product sentiment and making suggestions using state-of-the-art machine learning and deep learning algorithms requires a comprehensive pipeline. Thus, this paper addresses the need for a comprehensive pipeline to analyze online product sentiment and recommend products using advanced machine learning and deep learning algorithms. The methodology of the research is divided into two parts: the Sentiment Analysis Approach and the Product Recommendation Approach. The study applies several state-of-the-art algorithms, including Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, Bidirectional Long-Short-Term-Memory (BI-LSTM), Convolutional Neural Network (CNN), Long-Short-Term-Memory (LSTM), and Stacked LSTM, with proper hyperparameter optimization techniques. The study also uses the collaborative filtering approach with the k-Nearest Neighbours (KNN) model to recommend products. Among these models, Random Forest achieved the highest accuracy of 95%, while the LSTM model scored 79%. The proposed model is evaluated using Receiver Operating Characteristic (ROC) -Area under the ROC Curve (AUC). Additionally, the study conducted exploratory data analysis, including Bundle or Bought-Together analysis, point of interest-based analysis, and sentiment analysis on reviews (1996-2018). Overall, the study achieves its objectives and proposes an adaptable solution for real-life scenarios.

show abstract

Section: Results Analysismentioning

confidence: 99%

“…The computational approach can be taken into consideration. Nowadays, machine learning algorithms have widely been utilized in biomedical imaging, forecasting things or even critical disease prognosis [7]. For the case of product analysis, it has shown their promising performance beforehand.…”

Section: Introductionmentioning

confidence: 99%

Analyzing Sentiment in Terms of Online Feedback on Top of Users' Experiences

Alonazi

2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…The explanation is that social ties influence recruiting activists, a longing for glory, and disappointment with their homeland's lives than by ideological factors [26,27]. Furthermore, a study by [28] has proven that any sentiment analysis can be easily detected if the organisation leverages this vast growth of social media such as Twitter and Facebook as their early detection of cyber threats. Hence, this model emphasises publishing any suitable counternarrative publicly on social media because it can influence and invite future collaboration with other agencies to give online awareness and digital platform sharing.…”

Section: Discussionmentioning

confidence: 99%

Counter-Narrative Cyber Security Model to Address the Issues of Cyber Terrorism

Ahmad Tamerin,

Bakar,

Hassan

et al. 2023

OIJI

View full text Add to dashboard Cite

Terrorism is the imminent threat that Malaysia and the entire world are facing nowadays. This has become a severe threat to Malaysia’s national security as extremist groups such as ISIS and DAESH are leveraging cyberspace to gain more supporters and sympathisers. These extremists used social media to disseminate their narratives among the Malaysian Armed Force (MAF) personnel to recruit them for their excellent military skills. Nevertheless, the current MAF counter-narrative is still using traditional media operations like roadshows, brochures dissemination, articles, and short videos in combating the terrorism agenda, which are less effective and time-consuming. Therefore, this study proposes an enhanced counter-terrorism approach to fight this terrorism narrative by utilising the MAF IT infrastructure to focus on the social media platform. The model was built based on ISO / IEC 27032:2012 standard, concerning three cyber-terrorism models. Six military IT experts then verified this new enhanced model. They agreed that it is crucial to establish such a model and emphasise that counter-terrorism effort needs full cooperation with other services and collegiality. This study’s final output is the Counter-Narrative Information Technology Model, which will later potentially be adopted to the MAF environment in line with the national inspiration in fighting terrorism.

show abstract

Sentiment analysis for product rating using a deep learning approach

Mohbey

2021

2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS)

View full text Add to dashboard Cite

Sentiment Analysis of Electronics Product Tweets Using Big Data Framework

Cited by 9 publications

References 0 publications

Analyzing Sentiment in Terms of Online Feedback on Top of Users' Experiences

Analyzing Sentiment in Terms of Online Feedback on Top of Users' Experiences

Counter-Narrative Cyber Security Model to Address the Issues of Cyber Terrorism

Sentiment analysis for product rating using a deep learning approach

Contact Info

Product

Resources

About