In recent years, traffic has emerged as a
ubiquitous problem faced by thousands of commuters on
daily basis. With the, ever-increasing number of vehicles
emerging on road, the problem does not seem to fade away. It
poses a strikingly major conundrum to a large number of
people. Using the analysis we use Twitter as our Database
and aim to find the traffic-prone areas (e.g. In Delhi) so that
people are familiar with the areas, which are highly prone to
Traffic. In this paper, we demonstrate how social media
content can be used to predict real-world outcomes. In
particular, we use tweets made from twitter handles to
forecast traffic prone areas in a specified region. We further
analyze those numbers using linear regression to find which
area is more prone to traffic.
Aastha Khanna : Department Of Information Technology, I.G.D.T.U.W,
Kashmere Gate, New Delhi 110006, India
Tanvi Malhotra : Department Of Information Technology, I.G.D.T.U.W,
Kashmere Gate, New Delhi 110006, India
Sonal Meena : Department Of Information Technology, I.G.D.T.U.W,
Kashmere Gate, New Delhi 110006, India
Dr. Kalpana Yadav : Department Of Information Technology, I.G.D.T.U.W,
Kashmere Gate, New Delhi 110006, India
Twitter
Data Mining
Traffic Police
Linear
Regression
After applying the regression models and analyzing the data
in detail, we realized that traffic prone is an essential
problem faced by 1.8 crores commuters in Delhi on daily
basis.
[1] Emilio Ferrara, Pasquale De Meo, Giacomo Fiumara,
Robert Baumgartner, Center for Complex Network and
Sustem Research, Indiana University, Bloomington,
“Web Data Exraction, Application and Technniques: A
survey”
[2] Sitaram Asur, Bernardo A Huberman, Social
Computing Lab, HP labs, “Predicting the future with
Social Media”
[3] Narashima S Purohit, Meghana Bhat, Akshata B
Angadi, Karuna C Gull, Department of Computer
Science and Engineering, K.L.I.E.T, “Crawling
through Web to Extract the Data from Social
Networking Site- Twitter”,
[4] Adam Tsakalidis, Symeon Papadupoulus, Alexendra I.
Ccristea, Yiannis Kompatsiaris, “Predicitng Elections
for Multiple Countries Using Twitter and Polls”, 2015
[5] Bernardo A Huberman, Daniel M Romero and Fang
Wu. Social Nteworks that matter: Twitter under the
microscope. Jan 2009
[6] http://en.wikipedia.org/wiki/PECOTA
[7] http://www.pearanalytics.com/blog/2009/twitter-studyreveals-
interesting-results-40-percent-pointless-babble/
[8] The Collinearity Problem in Linear Regression. The
Partial Least Squares (PLS) Approach to Generalized
Inverses S. Wold, A. Ruhe, H. Wold, and W. J. Dunn,
III
[9] M. Young, The Technical Writer’s Handbook. Mill
Valley, CA: University Science, 1989.
[10] P.Ruchi and K. Kamalkar, “ET: Event from tweets,” in
Proc. 22nd Int. Conf. Worl Wide Web Comput, Rio de
Janeiro, Brazil, 2013