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

Table 1.

A summary of the related work.

More »

Table 1 Expand

Table 2.

A sample of the dataset available at IEEE data port [30].

More »

Table 2 Expand

Table 3.

A comparison of sentiment scores between those provided by IEEE data port (SS1) and those determined by our approach after preprocessing (SS2).

More »

Table 3 Expand

Table 4.

Counts of tweets within the three classes.

More »

Table 4 Expand

Fig 1.

Term counts in Covid-19 tweets dataset [30].

More »

Fig 1 Expand

Fig 2.

The word-cloud to highlight the topics after preprocessing.

More »

Fig 2 Expand

Table 5.

The parameter settings of five machine learning models.

More »

Table 5 Expand

Fig 3.

Our proposed approach based on concatenation of BoW and TF-IDF.

More »

Fig 3 Expand

Fig 4.

Our proposed methodology.

More »

Fig 4 Expand

Table 6.

Three sample tweets.

More »

Table 6 Expand

Table 7.

Sample tweets after removing usernames and links.

More »

Table 7 Expand

Table 8.

Sample tweets after removing punctuation marks and conversion to lower case.

More »

Table 8 Expand

Table 9.

Sample tweets after removing stopwords and numeric values.

More »

Table 9 Expand

Table 10.

Sample tweets after stemming.

More »

Table 10 Expand

Table 11.

The TextBlob performance on original data.

More »

Table 11 Expand

Table 12.

TextBlob performance after preprocessed data.

More »

Table 12 Expand

Table 13.

Training and testing tweets count for SS1 and SS2.

More »

Table 13 Expand

Table 14.

TF-IDF features on two sample tweets.

More »

Table 14 Expand

Table 15.

BoW features on two sample tweets.

More »

Table 15 Expand

Table 16.

Concatenated features on two sample tweets.

More »

Table 16 Expand

Table 17.

Models performance for SS1 using TF-IDF.

More »

Table 17 Expand

Table 18.

Models performance for SS1 using TF-IDF.

More »

Table 18 Expand

Fig 5.

ETC confusion matrix using SS1 and SS2 under TF-IDF features.

More »

Fig 5 Expand

Table 19.

Models performance for SS1 using BoW.

More »

Table 19 Expand

Table 20.

Models performance for SS2 using BoW.

More »

Table 20 Expand

Fig 6.

ETC confusion metric for SS1 and SS2 under BoW features.

More »

Fig 6 Expand

Table 21.

Models performance for SS1 using TF-IDF and BoW concatenation.

More »

Table 21 Expand

Table 22.

Models performance for SS2 using TF-IDF and BoW concatenation.

More »

Table 22 Expand

Fig 7.

ETC confusion matrix for SS1 and SS2 using concatenated features.

More »

Fig 7 Expand

Table 23.

Models accuracy performance comparison for SS2 and Vader.

More »

Table 23 Expand

Fig 8.

Models accuracy performance for SS1, SS2 and Vader using concatenated feature engineering technique.

More »

Fig 8 Expand

Table 24.

Model accuracy performance comparison on SS2 with GloVe, CNN-LSTM, DNN and concatenated features.

More »

Table 24 Expand

Fig 9.

Models accuracy performance for SS2 using the concatenated feature engineering technique.

More »

Fig 9 Expand