• Arif Md. Sattar
• Dr. Sanjay Kr. Tiwari
• Mritunjay Kr. Ranjan

It is possible that in many of today's applications for big data analytics, it will require to evaluate feeds from social media in addition to visualising the views of users. This will give a workable alternative source that we may use to determine new measurements for our digital lives. The open-ended nature of social engagement with other users on Twitter makes media analysis on Twitter much simpler when compared to study of other social media. This is due to the fact that the majority of these forms of communication are private, which results in a distinctive mode of engagement. As a result, the emphasis of this study is narrowed down to the design and implementation of a deep model for visualisation of Twitter opinions (moods) that is based on a deep learning network. It is concerned with Natural Language Processing (NLP)-based sentiment analysis using the Deep Learning framework for the visualisation and categorization of opinions mined from Twitter. The approach that is applied is based on applying natural language processing (NLP) sentiment analysis to a large number of tweets in order to display the projected mood score of the tweet and, as a result, to capitalise on public tweeting for the purpose of knowledge discovery. In addition to that, this will help in the identification of bogus news. The relevant mechanism is comprised of a series of sequential stages, including the stage of dataset collection, the stage of pre-processing, the stage of natural language processing, the stage of sentiment analysis, and the stage of prediction and classification using a deep learning model. The Sentiment Analysis of United States Airlines The dataset from Twitter, which is already available via Data for Everyone, was leveraged for this study. The device being shown is capable of monitoring Twitter streams coming from both the media and the general population. It is able to view and extract significant data from tweets in real time, and then store that data in a Deep model so that it can be analysed afterwards. It is handy for a broad range of applications, including big data analytics solutions, anticipating the behaviour of e-commerce customers, optimising marketing strategy, and gaining a competitive edge in the market, in addition to visualisation in other data mining applications.

Key words: Deep learning, data mining and web mining, visualization in social networks, NLP and sentiment analysis, machine learning.

"Model for Twitter Mood Visualization and Prediction Based on Deep Learning Approach Deep Tweets Analyzer Model for Twitter.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 11, page no.f728-f741, November-2022, Available :http://www.jetir.org/papers/JETIR2211596.pdf

"Model for Twitter Mood Visualization and Prediction Based on Deep Learning Approach Deep Tweets Analyzer Model for Twitter.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 11, page no. ppf728-f741, November-2022, Available at : http://www.jetir.org/papers/JETIR2211596.pdf