European Journal of Molecular & Clinical Medicine

The Stock market is a shambolic place for prediction as there are plenty of factors that affect the stock market simultaneously. Numerous studies have been conducted regarding this field, in hopes that one day accurate stock values can be predicted. This paper introduces a hybrid algorithm that incorporates Twitter sentiment analysis and Long Short Term Memory to predict next day closing values of a stock. Our proposed algorithm exploits the temporal correlation between public sentiment and its effect on stock values. We use Part-of-speech tagging to perform sentiment analysis and Long Short Term Memory for foretelling the next day closing price of the stock, both of these combined gives us a decent picture regarding the future of the stock.

Social media is a source that produces massive amount of data on an unprecedented scale. It serves as a platform for every person to share their perspectives, opinions and experiences apart from just being a platform that gives information to the public who search for information on the disease. As unexpected as the occurrence of coronavirus disease 2019 (COVID-19) was, it has been radically affecting people all over the world, there is a need to analyse the opinion of people on the pandemic COVID-19. This paper focuses on the sentiment analysis of COVID-19 using twitter data. The analyses are based on the machine learning algorithms. This article provides an analysis on how people react to a pandemic outbreak, how much they are aware of the disease and its symptoms, what precautionary measures they are taking and whether or not people are following government’s guidelines etc. Understanding the posts on social media pages during a pandemic outbreak allows health agencies and volunteers to better assess and understand the public's insolences, sentiments and needs in order to deliver appropriate and effective information.

Utilization over Internet has been altogether expanded during most recent couple of
decades. People groups saving additional time via web based networking media locales. In
this exploration proposition, we are intrigued to anticipate the character of clients by
assessing their tweets. Up to this point, to accurately measure customer’s characters, they
predictable to get a character test. Th is made it unrealistic to utilize character examination
in plentiful online networking spaces. In this examination proposition, we apply neural
systems by which a client's character can be precisely anticipated through the freely
accessible data on their T witter profile. We will portray the sort of information gathered,
our strategies for assessment , and the AI methods that permit us to effectively foresee
character. This data is essential for organizations to target possible buyers or look for client
suppo sitions in case of enhancement as a business methodology. In this way, this work
examines online networking information to anticipate huge character characteristics, for
example characteristics or qualities explicit to a person. The main strides towards we b
based life locales, raises information size and volume. The measure of information that is
transferred to these person to person communication administrations is expanding step by
step. Along these lines, there is gigantic prerequisite to contemplate the exceptionally
unique conduct of clients towards these administrations. This is a starter work to
demonstrate the client designs and to contemplate the viability of AI prescient displaying
approaches on driving long range interpersonal communication admini stration Facebook.
We demonstrated the client remark patters, over the post on F B Pages anticipated that
what number of comments a position is required to obtain in next H h ou rs.

The online social media networks have become an important source for detecting real-world happenings in this modern digital world. Event detection has become an essential research topic nowadays because it illustrates different scenarios during crisis or events as it contains significant information about them. Several approaches exist for detecting and analyzing events which provide valuable information for various applications like disaster and crisis management, detecting disease outbreak, health monitoring, traffic management and opinion mining. Traditional event detection methods that are proposed for handling large, formal and structured documents are not suitable for social media networks due to its unique characteristics such as restricted length, unstructured phrases, time sensitivity and massive information. This article provides a survey of methods used for detecting event in online social media and also gives an outline of challenges that are faced in handling social media post.