• Apurva Dadhwal
• K.L Bansal

Tweets pre-process and extract unigram features after pre-processing of the tweets. In pre-processing, the noisy data is removed by using tokenization; stop word removal and stemming these processes remove the duplicate data like to repeat words, hash tags and emojis. These features and label learn by KNN, SVM and a hybrid of KNN and SVM. In thesis work, the proposed approach uses artificial neural network which gets improved by Multilayer perceptron (ANN-MLP or MLP-ANN). The proposed approach involves a nonlinear mapping of features and refined results by hidden layer. The experimental analysis shows that ANN-MLP improves all metrics like precision, recall and accuracy. So, it further indicates that the proposed approach improves the tweet sentiment classification results under 5-cross validation and 10-cross validation.

ANN, MLP, tweets, sentiments, KNN

"MEASURING PERFORMANCE OF SVM,KNN,HYBRID AND ANN(MLP) ON BASIS OF ACCURACY AND PRECISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.284-290, June-2019, Available :http://www.jetir.org/papers/JETIR1906B42.pdf

"MEASURING PERFORMANCE OF SVM,KNN,HYBRID AND ANN(MLP) ON BASIS OF ACCURACY AND PRECISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp284-290, June-2019, Available at : http://www.jetir.org/papers/JETIR1906B42.pdf