Call for Papers:Vol.10 Issue.6

Submission
Last date		 30-Dec-2024
Acceptance Status In One Day
Paper Publish In Two Days
Submit ManuScript

News & Updates

Submit Article

Dear Authors, Article publish in our journal for Volume-10,Issue-6. For article submission on below link: Submit Manuscript


Join As Board

Dear Reviewer, You can join our Reviewer team without given any charges in our journal. Submit Details on below link: Join As Board


Paper Publication Charges

IJARIIE APP
Download Android App

For Authors

Archives

IJARIIE Board

Downloads

Android App

Download IJARIIE APP

Authors

Title: :  Location Inference for Non-geotagged Tweets in User Timelines
PaperId: :  13993
Published in:   International Journal Of Advance Research And Innovative Ideas In Education
Publisher:   IJARIIE
e-ISSN:   2395-4396
Volume/Issue:    Volume 7 Issue 2 2021
DUI:    16.0415/IJARIIE-13993
Licence: :   IJARIIE is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author NameAuthor Institute
Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.DK.S.RANGASAMY COLLEGE OF TECHNOLOGY
S.KALIMUTHUK.S.RANGASAMY COLLEGE OF TECHNOLOGY

Abstract

COMPUTER SCIENCE AND ENGINEERING
REAL-TIME, Location, User Timeline, Tweets, Accuracy.
Online media like Twitter have gotten all around the world well known in the previous decade. This pattern has added to encourage different area put together administrations conveyed with respect to online media, the accomplishment of which vigorously relies upon the accessibility and precision of clients' area data. We tackle this issue by examining Twitter client courses of events in a novel manner. Above all else, we split every client's tweet timetable transiently into various bunches, each having a tendency to suggest an unmistakable area. Accordingly, we adjust two AI models to our setting and plan classifiers that characterize each tweet group into one of the pre-characterized area classes at the city level. The Bayes put together model concentrations with respect to the data gain of words with area suggestions in the client produced substance. The convolutional LSTM model treats client created substance and their related areas as successions and utilizes bidirectional LSTM and convolution activity to make area surmising’s. The exploratory outcomes propose that our models are viable at inducing areas for non-retagged tweets and the models beat the best in class and elective methodologies essentially as far as surmising exactness Area induction for tweets are tested by two significant issues. To start with, Twitter restricts the length of each tweet substance to 140 characters, and consequently a tweet just contains few words and passes on restricted data. Second, Twitter clients regularly utilize non-standard and shorthand terms, and tweets are frequently muddled and loud. Thus, discovering area signs from short, loud tweets is obviously troublesome. Accordingly, two AI models are painstakingly adjusted to our difficult setting and classifiers are intended to order each tweet bunch from a client's course of events into one of the pre-characterized area classes at the city level. The Bayes put together model concentrations with respect to the data gain of words with area suggestions in the client created substance, while the LSTM based model treats client produced substance and their related areas as groupings and utilizes a bidirectional LSTM and convolution activity to make area derivations. Our models are prepared utilizing disconnected information, however they can be utilized to gather areas for recorded tweets and web based (approaching) tweets. The two models are tentatively assessed on a huge genuine dataset, in examination with elective methodologies. The test results recommend that the proposed models are powerful at surmising areas for tweets and they beat choices essentially regarding derivation accuracy. Compared with existing methodologies, our methodology abuses the transient data in an unexpected way. A transient bunching method is utilized to part each Twitter client's courses of events into groups every one of which is relied upon to contain tweets posted at a similar area. In contrast to existing methodologies, our own adjusts a profound learning model which accomplishes high precision while deriving areas for singular tweets apparently, this is the principal work on applying a profound learning model to tweet area derivation. The latest examination to appraise tweet areas at the city level, we contrast our methodology and it in the exploratory investigation. The outcomes show that our own accomplishes essentially better area derivation result.

Citations

Copy and paste a formatted citation or use one of the links to import into a bibliography manager and reference.

IJARIIE Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. "Location Inference for Non-geotagged Tweets in User Timelines" International Journal Of Advance Research And Innovative Ideas In Education Volume 7 Issue 2 2021 Page 1364-1369
MLA Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. "Location Inference for Non-geotagged Tweets in User Timelines." International Journal Of Advance Research And Innovative Ideas In Education 7.2(2021) : 1364-1369.
APA Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, & S.KALIMUTHU. (2021). Location Inference for Non-geotagged Tweets in User Timelines. International Journal Of Advance Research And Innovative Ideas In Education, 7(2), 1364-1369.
Chicago Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. "Location Inference for Non-geotagged Tweets in User Timelines." International Journal Of Advance Research And Innovative Ideas In Education 7, no. 2 (2021) : 1364-1369.
Oxford Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. 'Location Inference for Non-geotagged Tweets in User Timelines', International Journal Of Advance Research And Innovative Ideas In Education, vol. 7, no. 2, 2021, p. 1364-1369. Available from IJARIIE, https://ijariie.com/AdminUploadPdf/Location_Inference_for_Non_geotagged_Tweets_in_User_Timelines_ijariie13993.pdf (Accessed : ).
Harvard Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. (2021) 'Location Inference for Non-geotagged Tweets in User Timelines', International Journal Of Advance Research And Innovative Ideas In Education, 7(2), pp. 1364-1369IJARIIE [Online]. Available at: https://ijariie.com/AdminUploadPdf/Location_Inference_for_Non_geotagged_Tweets_in_User_Timelines_ijariie13993.pdf (Accessed : )
IEEE Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU, "Location Inference for Non-geotagged Tweets in User Timelines," International Journal Of Advance Research And Innovative Ideas In Education, vol. 7, no. 2, pp. 1364-1369, Mar-App 2021. [Online]. Available: https://ijariie.com/AdminUploadPdf/Location_Inference_for_Non_geotagged_Tweets_in_User_Timelines_ijariie13993.pdf [Accessed : ].
Turabian Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. "Location Inference for Non-geotagged Tweets in User Timelines." International Journal Of Advance Research And Innovative Ideas In Education [Online]. volume 7 number 2 ().
Vancouver Dr.D.MUTHUSANKAR, B.Tech.,M.E., Ph.D, and S.KALIMUTHU. Location Inference for Non-geotagged Tweets in User Timelines. International Journal Of Advance Research And Innovative Ideas In Education [Internet]. 2021 [Cited : ]; 7(2) : 1364-1369. Available from: https://ijariie.com/AdminUploadPdf/Location_Inference_for_Non_geotagged_Tweets_in_User_Timelines_ijariie13993.pdf
BibTex EndNote RefMan RefWorks

Number Of Downloads



Save in Google Drive

Similar-Paper

TitleArea of ResearchAuther NameAction
Development of Wireless Sensor Network Protocol using Fuzzy logic and Optimization Routing AlgorithmComputer ScienceMs.Dimpal Patel Download
GreenTech Urbanism: The Role of IoT and Machine Learning in Environmental MonitoringComputer Science and EngineeringSowmya Shetty Download
SURVEY ON DETECTION OF PHISHING WEBSITE USING MACHINE LEARNINGComputer Science and EngineeringYawalkar Prasad Pramod Download
Enhancement of Health Data Accuracy Using Neural Network Algorithmneaural networkGautam Prakash Download
AI-BASED PLACEMENT PARTNER: ENHANCING CAREER PREPARATION THROUGH ADVANCED LEARNING TECHNOLOGIESComputer Science & EngineeringSaranya MK Download
ARTIFICIAL INTELLIGENCE IN HEALTH CARE - AN OVERVIEWComputer EngineeringPaleti Surekha Download
A Comparative Study of Maze-Solving Algorithms: Performance, Complexity, and Practical Applications in AI and RoboticsComputer EngineeringNakka Sai Magh Reddy Download
Encryption and Decryption WebsiteComputer Science and EngineeringGokul Kumar R Download
Digital BiomarkersComputer EngineeringHemakanth Sharma R Download
ENSURING FAIRNESS AND TRANSPARENCY IN AI SYSTEMS FOR HEALTHCARE AND CRIMINAL JUSTICE APPLICATIONSComputer EngineeringManu Gowda Download
Utilising AI for Deepfake Detection: Strategies, Issues and Future OpportunitiesArtificial intelligence Suhas LK Download
Cryptography-An OverviewComputer EngineeringPeram Bairaveswar Reddy Download
The Internet of Things (IoT) in Smart CitiesComputer engineeringRahul Malagitti Download
Cloud Computing - An OverviewComputer EngineeringHarshith Y Download
Operations of Artifical Intelligence in 5g NetworkingComputer Engineering Chethan K Download
12