An intelligent hybrid feature Ensemble model and mixed cnn for Prediction of mental depression Disorder using tweets

dc.contributor.guideBalasubramanie, P
dc.coverage.spatialAn intelligent hybrid feature Ensemble model and mixed cnn for Prediction of mental depression Disorder using tweets
dc.creator.researcherVivek, D
dc.date.accessioned2022-12-24T07:38:23Z
dc.date.available2022-12-24T07:38:23Z
dc.date.awarded2021
dc.date.completed2021
dc.date.registered
dc.description.abstractIn the recent days, the number of people affected by Mental newlineDepression Disorder (MDD) is on the rise with age, occupation related stress newlinelevels and several other factors. Depression has been identified as the main newlinecause behind various diseases in individuals. In most cases, mental depression newlinedisorder is diagnosed with the help of counselling given by psychiatrists. newlineHowever, even after the counselling and clinical diagnosis, the symptoms of newlinedepression persist. Social stigma associated with depression results in newlinereluctance on the part of individuals to consult psychiatrists to diagnose newlinemental illness. Also the existing techniques or methods do not guarantee newlineaccurate prediction of the level of depression. In order to overcome these newlineproblems, a new emotional model is designed to analyze the depression in newlineindividuals. A set of questionnaires called Personal Survey Questionnaire newline(PSQ) is framed to collect responses from the tweeters to understand about newlinetheir mindset and depression level. Based on the PSQ answers, E-Ranking is newlinecalculated and compared with the polarity value generated by the PSQ newlineanswers. The performance of the proposed questionnaire-based model is newlinecompared with seven existing model based on parameters such as estimate newlineand P-Value. newlineAs the questionnaires alone do not give the best prediction of the newlinedepression level, as a second phase of this research work, the social media newlinedata is utilized to predict the level of depression. The use of social media newlineamong people has been widely prevalent with individuals using social media newlineto provide their reviews about a product or event which are a reflection of newlinetheir mindset and perception about the product or the event. However, newlinecollecting meaningful information from social media is a tedious task because newlineof its unstructured nature. The rate of unstructured newline
dc.description.note
dc.format.accompanyingmaterialNone
dc.format.dimensions21cm
dc.format.extentxix, 139p.
dc.identifier.urihttp://hdl.handle.net/10603/430901
dc.languageEnglish
dc.publisher.institutionFaculty of Information and Communication Engineering
dc.publisher.placeChennai
dc.publisher.universityAnna University
dc.relationp.123-138
dc.rightsuniversity
dc.source.universityUniversity
dc.subject.keywordEngineering and Technology
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Information Systems
dc.subject.keywordmental depression
dc.subject.keywordDisorder using tweets
dc.titleAn intelligent hybrid feature Ensemble model and mixed cnn for Prediction of mental depression Disorder using tweets
dc.title.alternative
dc.type.degreePh.D.

Files

Original bundle

Now showing 1 - 5 of 14
Loading...
Thumbnail Image
Name:
01_title.pdf
Size:
22.66 KB
Format:
Adobe Portable Document Format
Description:
Attached File
Loading...
Thumbnail Image
Name:
02_prelim pages.pdf
Size:
2.63 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
03_content.pdf
Size:
11.1 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
04_abstract.pdf
Size:
7.24 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
05_chapter 1.pdf
Size:
109.89 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: