ML methods | Reference | Objectives | Materials | Output |
---|---|---|---|---|
NB | [6] | To present a continuous Naïve Bayes learning framework for e-commerce product review sentiment classification | E-commerce review and Cornell Movie review dataset | Positive, negative and neutral |
 | [24] | To develop a workflow for applying sentiment analysis in detecting public emotions in natural disaster crises | Twitter (Kashmir Floods) | Negative, positive and neutral |
 | [23] | To explore consumer attitudes and experiences of "train operating companies." | Twitter (tweets on train operating companies) | Positive or negative |
 | [36] | To access and classify Tweets for counter violent extremism and the spread of extremist content on Twitter | Twitter Data | Positive, negative and neutral |
 | [37] | To investigate tourist emotions on their travel experiences targeting Gatlinburg, Tennessee | Online reviews of Tripadvisor | Emotions (anger, disgust, fear, joy, sadness and surprise) |
 | [21] | To analyse every food review of the user and classify if it is positive, negative or neutral | McDonald’s dataset is customer reviews | Positive, negative and neutral |
 | [38] | To monitor public opinion on trending topics on the social media platform | Positive, negative or neutral | |
 | [39] | To perform aspect-based sentiment analysis by filtering statements from the review pertinent and extracting sentiments from the reviews, and associating them with corresponding aspect categories | Amazon movie review dataset | Positivity or negativity |
NB + SVM | [40] | Analyse opinions on smartphone reviews | Smartphone reviews | Positive and negative |
 | [41] | Survey different types of sentiment analysis methods based on cryptocurrencies topic | Positive, neutral and negative | |
 | [42] | Identify the levels of positive and negative emotion in messages | Twitter comment, | unrelated, neutral, negative and positive messages |
 | [29] | To develop a polarity detection system on textual movie reviews in Bangla | Text movie review in Bangla | Positive or negative |
 | [28] | To implement a combination of user behaviour, semantic and lexical features together for finding polarity emotions of Tweets | Positive and negative | |
 | [43] | To analyse and consider traffic jam events where traffic will be able to move or will not be able to move | Twitter (traffic jams) | Positive, negative or neutral |
NB + SVM + DBN | [44] | To classify a Malay sentiment by proposing a classification model to improve classification performances | Online blogs and forums of Malaysian website | Positive and negative |
NB + DT | [45] | Find the polarity of any sentence by analysing the opinion of that particular sentence | Hindi sentences and reviews | Positive, neutral and negative |
NB + DT | [30] | To apply an efficient processing approach in handling Tweets, in both Arabic and English languages | Tweets Dataset (ASTD) and Restaurant Reviews Dataset (RES) Stanford Twitter dataset, Twitter US Airline Sentiment dataset and the Uber Ride Reviews dataset | Positive, negative and neutral |
NB + ME | [46] | To evaluate the accuracy of combining different parameters of machine-learning algorithms for consumer products | Positive or negative | |
NB + ME + SGD + SVM | [47] | To classify human sentiment-based movie reviews using various supervised machine learning algorithms To examine the accuracy of different methods | Internet Movie Database (IMDB) | Positive, negative and neutral |
NB + LR + DT | [48] | To perform tweets classification with the help of Apache Spark framework | Twitter dataset (Kaggle and Twitter Sentiment Corpus) | Positive, negative or neutral |
CNN + NB + J48 (DT) + BFTree, OneR + LDA + SVM | [49] | Introduce and examine the proposed technique with Convolution Neural Network used for text classification | IMDB movie portal, Amazon product reviews | Positive negative and neutral |
SVM + NB + RF | [20] | To provide sentiment mining in extracted sentiment from Twitter Social App for analysis of the current trending topic in India and its impact on different sectors of the Indian economy | Tweets | Positive, negative and neutral |
SVM + NB + RF | [50] | Mining consumer reviews with a machine learning approach by converting reviews into vector representations for classification | Amazon review dataset | Positive or negative |
Multinomial NB + SVM | [51] | Develop an efficient review classification | Reviews TripAdvisor dataset | Positive and negative |
SVM + Multinomial NB + LR + RF | [52] | To develop a clinical decision support system for the personalised therapy process | Drug review dataset | Positive, negative or neutral |
SVM + CRF + Multinomial NB | [53] | To present an ensemble framework of text classification which reviews products | Twitter and product review | Positive and negative |
Multinomial NB + SVM + LR | [54] | To compare the performance of different machine learning algorithms in performing sentiment analysis of Twitter data | Positive or negative | |
DT + Multinomial NB + SVM | [55] | To investigate three approaches for emotion classification of opinions in the Thai language | Customer reviews of cosmetics Thai | Positive and negative |
SVM + Multinomial NB + DNN | [56] | To compare multiple state-of-the-art models capable of classifying game reviews as positive, negative or neutral | Games reviews | Positive, neutral and negative |
Bernoulli NB + SVM + RF + NNs + LR | [57] | To present a comparison among several sentiment analysis classifiers in the learning environment | Twitter (educational opinions in an Intelligent Learning Environment) | Emotions positive or negative, engagement, excited, boredom and frustration |
LR + k-NN + SVM + DT + RF + Ada Boost + Gaussian NB | [58] | To analyse the reviews posted by people at four different product websites | Amazon reviews, Yelp reviews, IMDB reviews, Indian Airlines reviews | Positive and negative |