Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Methodology and research design.

More »

Fig 1 Expand

Table 1.

Results from the training and testing sets.

More »

Table 1 Expand

Table 2.

Statistical report on recommendation classification using logistic regression with count vectorizer.

More »

Table 2 Expand

Fig 2.

Confusion matrix of LR with count vectorizer.

More »

Fig 2 Expand

Table 3.

Statistical Report on Recommendation Classification using Logistic Regression with TF-IDF Vectorizer.

More »

Table 3 Expand

Fig 3.

The confusion matrix of LR with TF-IDF vectorizer.

More »

Fig 3 Expand

Table 4.

Statistical report on recommendation classification using naive Bayes with count vectorizer.

More »

Table 4 Expand

Fig 4.

The confusion matrix of Naive Bayes with count vectorizer.

More »

Fig 4 Expand

Table 5.

Statistical report on recommendation classification using Naive Bayes with TF-IDF vectorizer.

More »

Table 5 Expand

Fig 5.

The confusion matrix of Naive Bayes with TF-IDF vectorization.

More »

Fig 5 Expand

Table 6.

Statistical Report on Recommendation Classification using SVM with Count Vectorizer.

More »

Table 6 Expand

Fig 6.

The confusion matrix of SVM with count vectorization.

More »

Fig 6 Expand

Table 7.

Statistical report on recommendation classification using SVM with TDF-IDF vectorizer.

More »

Table 7 Expand

Fig 7.

The confusion matrix of SVM with TF-IDF vectorization.

More »

Fig 7 Expand

Table 8.

Statistical report on recommendation classification by random forest with count vectorizer.

More »

Table 8 Expand

Fig 8.

Confusion matrix of RF with count vectorizer.

More »

Fig 8 Expand

Table 9.

Statistical report on recommendation classification by RF with TDF-IDF vectorizer.

More »

Table 9 Expand

Fig 9.

Confusion matrix of RF with TF-IDF Vectorizer.

More »

Fig 9 Expand

Table 10.

Statistical report on recommendation classification using ada boosting with count vectorizer.

More »

Table 10 Expand

Fig 10.

The confusion matrix of ada boosting with count vectorizer.

More »

Fig 10 Expand

Table 11.

Statistical report on recommendation classification via ada boosting with TDF-IDF vectorizer.

More »

Table 11 Expand

Fig 11.

The confusion matrix of ada boosting with TF-IDF vectorization.

More »

Fig 11 Expand

Table 12.

Statistical report on recommendation classification using deep learning GRU.

More »

Table 12 Expand

Fig 12.

Precision-recall curve for the deep learning model GRU.

More »

Fig 12 Expand

Table 13.

Statistical report on recommendation classification using bidirectional LSTM.

More »

Table 13 Expand

Fig 13.

The confusion matrix of LSTM.

More »

Fig 13 Expand

Table 14.

Performance metrics of classifiers with count vectorizer.

More »

Table 14 Expand

Table 15.

Performance metrics of classifiers with TF-IDF vectorizer.

More »

Table 15 Expand