Table 3. Open dataset analysis in predicting helpful reviews.
Performance of technique evaluation in predicting helpful reviews.
| Author., year | Dataset publicly availability | Technique | Performance matrices | Performance |
|---|---|---|---|---|
| Olmedilla, Martínez-Torres & Toral (2022) | No | Convolutional Neural Network | Accuracy | 66.00% |
| Son, Kim & Koh (2021) | No | Convolutional Neural Network | Accuracy | 70.70% |
| Woo & Mishra (2021) | No | Tobit Regression | Accuracy | 74.00% |
| Akbarabadi & Hosseini (2020) | No | Random Forest | Accuracy | 85.60% |
| Malik (2020) | Yes1 | Deep Neural Network | MSE | 0.06 |
| Anh, Nagai & Nguyen (2019) | Yes2 | Convolutional Neural Network | Accuracy | 70.13% |
| Eslami, Ghasemaghaei & Hassanein (2018) | No | Artificial Neural Network | Accuracy | 80.70% |
| Malik & Hussain (2018) | Yes3 | Stochastic Gradient Boosting | MSE | 0.05 |
| Liu et al. (2017) | No | Unigram Features + Argument-Based Features | Accuracy | 71.80% |
| Menner et al. (2016) | No | Keyword Clustering | Accuracy | 88.45% |
| Qazi et al. (2016) | No | Tobit Regression | Efron’s | 0.167 |
| Yang, Chen & Bao (2016) | No | Support Vector Machine | Correlation Coefficient | 0.665 |
| Huang et al. (2015) | No | Tobit Regression | Efron’s | 0.128 |
| Krishnamoorthy (2015) | Yes4 | Random Forest | Accuracy | 81.33% |
| Yang et al. (2015) | No | Support Vector Machine | Correlation Coefficient | 0.702 |
| Zhang et al. (2015) | No | Gain-based Fuzzy Rule-covering Classification | Accuracy | 72.80% |
| Martin & Pu (2014) | No | Random Forest | Accuracy | 88.00% |
| Zhang, Qi & Zhu (2014) | No | Linear Regression | Correlation Coefficient | 0.712 |
| Zeng et al. (2014) | No | Support Vector Machine | Accuracy | 72.82% |
| Momeni et al. (2013) | No | Random Forest | Accuracy | 89.00% |
| Korfiatis, García-Bariocanal & Sánchez-Alonso (2012) | No | Tobit Regression | Efron’s | 0.451 |
| Min & Park (2012) | No | Rule-Based Classifier | Accuracy | 83.33% |
| Wu, Van der Heijden & Korfiatis (2011) | No | Ordinary Least Square Regression | Correlation Coefficient | 0.607 |
| Ghose & Ipeirotis (2010) | No | Support Vector Machine | Accuracy | 87.68% |
| O’Mahony & Smyth (2010) | No | Random Forest | AUC Score | 0.77 |
| Susan & David (2010) | No | Tobit Regression | Efron’s | 0.420 |
| Otterbacher (2009) | No | Linear Simple Regression | Efron’s | 0.170 |
| Liu et al. (2008) | No | Non-Linear Regression | F-Measure | 71.16% |
| Weimer & Gurevych (2007) | No | Support Vector Machine | Accuracy | 77.39% |