Online ISSN: 2515-8260

Keywords : facebook

Detecting Untrue Information On Social Media Using Machine Learning

Dr.M.Rajaiah, Mr.N.Krishna Kumar, Ms.U.Indraja, Ms.T.Kusuma Kumari,Ms.Sk.Bhanu, Ms.K.Tejaswini

European Journal of Molecular & Clinical Medicine, 2023, Volume 10, Issue 4, Pages 1266-1271

These days, a lot of information is exchanged on social media, and it can be difficult to tell what information is accurate and what information is false. As soon as they read the content, people start sharing their problems or ideas without first checking your validity. Its spread is a result of this as well. The most common sources of misleading and unverified information are rumours and fake stories, which should be exposed as soon as possible to prevent their unexpected effects. Online forums are where most smart phone users choose to read tales. News websites disseminate breaking news and offer a source of confirmation. How to spread news and articles on social media platforms like WhatsApp groups, Facebook pages, Twitter, and other tiny blogs and social networking sites is the subject at hand. It is risky for the general population to take these rumours and news stories seriously. There is an urgent need to put an end to rumours, especially in growing nations like India, and to concentrate on legitimate, established issues. This essay demonstrates a paradigm and a technique for gathering misleading information. The proposed model's outcomes are contrasted with those of other models. The suggested model performs well and explains the results' accuracy to a maximum of 93.6% accuracy.


Dr.Mathivanan, Dr.MalarMoses , Dr. Anupama Roshan

European Journal of Molecular & Clinical Medicine, 2022, Volume 9, Issue 4, Pages 940-951

Internet addiction has become a health concern globally. Under internet addiction, there are five different type of addictions.To understand, treat, prevent internet addiction, it is essential to know the preferences given to various internet platforms and its associated demographic factors.
To find the preference of online platforms and associated demographic factorsamong internet users.
Materials and methods
Internet addiction severity was assessed by internet addiction test questionnaire (IAT-TN). Semi stuctured questionnaire was set up to collect socio demographic details including preference of online platforms by the users.Statistical analysis was done and the preferences given to online platforms and associated factors were evaluated.
In this study, 1367 people participated. Women watched mostly   facebook, whatsapp, youtube, videogames were 14.1%, 35.9%, 34.5%, 0.6% respectively. Men watched facebook, whatsapp, youtube, videogames were 33%, 27.8%, 27%, 2.6% respectively .
In the less than 18 years population group, mostly watched preferences were given to facebook, whatsapp, youtube, videogames were 4.8%, 11.9%, 57.1%, 14.3% respectively.  In 18 to 40 age group, it was found 27.7%, 23.2%, 34%, 1.5% respectively.  Among above 40 age group, it was found 23.5%, 50.6%, 17.8%, 1.3% respectively.
Unmarried population, mostly watched preference for facebook, whatsapp, youtube, videogame were 17.15%, 21.4%, 38.1%, 4% respectively . In married  population, it was found 30.7%, 36.5%, 25.2%, 0.6% respectively.
Men preferred Facebook,whatsapp, youtube more, while female preferred Whatsapp, youtube more.Below 18 age people were watching videogames than others.  In 18 to 40 age group, Youtube is the most watched one. In above 40 age group, Whatsappis the most watched.School population watched videogames more. Married people use internet for communication than game and entertainment. In this study we find significant difference in preference of internet platforms when considering age, gender, education and marital status.