ISSN (Online) :

 Special Issue on The Sustainable Development Goals

Notice Board

Call For Paper:

Vol. 7, October, Issue 6

Paper Submission  Deadline : 30th  October 2024

Vol. 7,  Special Issue(Bi-yearly)



OAIJSE Menu
Imp Links for Reviewer
Invites Proposal for


NONGEO TAGGED TWEETS IN USER TIMELINES FOR LOCATION INTERFERENCE FOR RESULT ANALYSIS

Abstract

Abstract: Web based life like Twitter have gotten all aroundwell known in the previous decade. Because of the high infiltration of cellphones, internet based life clients are progressively going portable. Thispattern has added to cultivate different area put together administrations sentwith respect to internet based life, the achievement of which intensely reliesupon the accessibility and exactness of clients' area data. In any case, just avery little part of tweets in Twitter are geo-tagged. In this way, it isimportant to derive areas for tweets so as to accomplish the reason for thosearea based administrations. In this paper, we handle this issue byinvestigating Twitter client courses of events in a novel manner. Above allelse, we split every client's tweet course of events transiently into variousgroups, each having a tendency to infer a particular area. Along these lines,we adjust two AI models to our setting and plan classifiers that characterizeeach tweet group into one of the pre-characterized area classes at the citylevel. The Bayes put together model concentrations with respect to the dataincrease of words with area suggestions in the client created substance. Theconvolutional LSTM model treats client created substance and their relatedareas as successions also, utilizes bidirectional LSTM and convolution activityto make area inductions. The two models are assessed on an enormous arrangementof genuine Twitter information. The test results propose that our models arecompelling at deducing areas for non-geotagged tweets and the models outflankthe best in class and elective methodologies altogether regarding surmisingexactness.

Keywords: Twitter,Location Inference, Bayes, LSTM

Full Text PDF
Impact Factor
Downloads
NEWS and Updates

Peer Review Process

 ICCEME -2024 conference     

Computer Science ,Electronics, Electrical  Engineering Information Technology, Civil, Computer Science and Engineering , Mechanical, Mechanical-Sandwich Petroleum, Production Instrumentation & Control, Automobile ,Chemical, Electronics Instrumentation& Control, Electronics & Telecommunication  Submit paper at oaijse@gmail.com



Open Access License Policy

Abstracted and Indexed In