User Feedback Severity Level Identification and Classification through Deeper Analysis of Text

Now a days world is look right on digitalized. Social media is captivating in this digital age through the accessibility of consumer's feedback. The recent work in the field of classification based on comments on social media is gaining appeal on a global scale. Unfortunately, the study does not offer better accuracy in terms of toxic comments. On social media platforms, hateful and abusive language has a detrimental effect on users' mental health and involvement from people from all diverse backgrounds. Automatic methods is most commonly used datasets with categorical labels to detect foul language. The level of offensiveness of comments varies. In NLP we use binary classification like either a comment is offensive or not and leave continues classification. In continues classification one can identify the severity level of comments, can set a threshold, and by using Deep Learning and modeling techniques can directly identify the severity level of comments by considering context. The review of related literature shows that identification of toxicity of user comments can be improved by pre-processing methods, such as deleting null values and anomies from the dataset, to refine the dataset and increase its accuracy by applying different algorithm techniques to make feature more valuables. This research provides analysis of user comments datasets and study's user comments toxicity with different machine learning approaches. First, we need to do pre-processing steps including punctuations, stop words, null entries, and duplicate removal to remove anomalies. After that we need to apply different methods like count vectorizer and bag of words to extract features. After that, we MCPL algorithm applied on these datasets to predicts results. By applying MCPL model on user comments dataset 88.5% accuracy were founded.