Online ISSN: 2515-8260

Keywords : Text mining

Impact Of Social Media On The Stock Market: Evidence From Tweets

Akshat Bani,Harsh Tiwari,Harsh Kumar,Aarish Ahmed,Ms. Shinki K Pandey .

European Journal of Molecular & Clinical Medicine, 2023, Volume 10, Issue 1, Pages 697-715

The paper deals with the impact of the economic agent sentiment on the return for Apple and Microsoft stocks. We employed text mining procedures to analyze Twitter messages with either negative or positive sentiment towards the chosen stock titles. Those sentiments were identified by developed algorithms which are capable of identifying sentiment towards companies and also counting the numbers of tweets in the same group. This resulted in counts of tweets with positive and negative sentiment. Then we ran analysis in order to find causality between sentiment levels and the stock price of companies. To identify causal effects we applied Granger causality tests. We found bilateral causality between the risk premium and the amount of news distributed by Twitter messages.


Jaichandran R; Leelavathy S; Kanaga Suba Raja; Pranav Kumar; Sailendra Kumar Majhi; Vikas Singh Thakur

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2800-2807

In this competitive era, getting right education and right job is always a challenge. Organization who are in need of skilled people in certain departments also find it difficult to identify right candidate with good talented skill set. In the proposed system, we propose 2 logins namely job seeker and employer. The proposed system tries to make the recruitment process simpler and efficient by integrating text mining and natural language processing techniques. The proposed architecture consists of unique and essential features like study materials, de-duplication process, resume analysis and weightage analysis. The employer can upload study materials while posting the job requirement so that the job seeker will have a fair knowledge of the exact job role. The recommendation of exact profile based on the skill required is processed using collaborative filtering algorithm. To optimize the cloud storage we have integrated de-duplication technique to eliminate saving same resume n number of times which would increase encryption cost and storage. The de-duplicaton process is performed using Proactive Replica Checking approach (PRCR). Also applying natural processing techniques in both job seeker and employer side provides efficient results saving much of time. In the employer side, we use web crawler to extract job description and requirements. In the job seeker side, once the resume is posted, stop word filtering and text segmentation is performed. After text segmentation, the scoring is provide based on the education, work experience, skills, personality traits and frequency of degree. Finally our proposed system provides a recommendation system for the upcoming generation in which degree of education major job requirements are coming.