Scribd
Upload
57 views16 pages

Under The Guidance of DR Manohar M: O.Rushikesavareddy-1860340

The document discusses location prediction on Twitter using machine learning techniques. It describes predicting a user's location from their tweets. The system architecture includes modules for data preprocessing, machine learning algorithms like naive bayes, decision trees and SVM, and classifying locations as home, mentioned or tweet location. Decision trees were found to be most suitable for tweet text analysis and location prediction due to the noisy nature of tweets.

Uploaded by

naveen kumar reddy sontireddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
57 views16 pages

Under The Guidance of DR Manohar M: O.Rushikesavareddy-1860340

The document discusses location prediction on Twitter using machine learning techniques. It describes predicting a user's location from their tweets. The system architecture includes modules for data preprocessing, machine learning algorithms like naive bayes, decision trees and SVM, and classifying locations as home, mentioned or tweet location. Decision trees were found to be most suitable for tweet text analysis and location prediction due to the noisy nature of tweets.

Uploaded by

naveen kumar reddy sontireddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Location Prediction on Twitter using Machine Learning Techniques

O.RushikesavaReddy-1860340

Under the guidance of Dr Manohar M

Mission Vision Core Values


Christ University is a nurturing ground for an Excellence and Service Faith in God | Moral Uprightness
individual’s holistic development to make effective Love of Fellow Beings | Social
contribution to the society in a dynamic environment Responsibility | Pursuit of Excellence
Christ University

Agenda of the presentation

• Abstract
• Introduction
• System Architecture
• Modules
• Conclusion
• References

Excellence and Service


Christ University

Abstract

Location prediction of users from online social media brings considerable research
these days. Automatic recognition of location related with or referenced in records
has been investigated for decades. As a standout amongst the online social network
organization, Twitter has pulled in an extensive number of users who send a
millions of tweets on regular schedule. Because of the worldwide inclusion of its
users and continuous tweets, location prediction on Twitter has increased
noteworthy consideration in these days. Tweets, the short and noisy and rich
natured texts bring many challenges in research area for researchers. In proposed
framework, a general picture of location prediction using tweets is studied. In
particular, tweet location is predicted from tweet contents. By outlining tweet
content and contexts, it is fundamentally featured that how the issues rely upon
these text inputs. In this work, we predict the location of user from the tweet text
exploiting machine learning techniques namely naïve bayes, Support Vector
Machine and Decision Tree.

Excellence and Service


Christ University

Introduction project
Users may post explicitly their location on the tweet text they post, whereas in certain
cases the location may be available implicitly by including certain relevant criteria.
Tweets are not a strongly typed language, in which users may post casual with
emotion images. Abbreviated form of text, misspellings, and extra characters of
emotional words makes tweet texts noisy. The techniques applied for normal
documents are not suited for analyzing tweets. The character limitations of tweets
about 140 characters may make the tweet uneasy to understand, if the tweet context
is not studied. The issue of location prediction related named as geolocation perdition
is examined for Wikipedia and web page documents. Entity recognition from these
formal documents has been researched for years. Different types of content and
context handling on these documents are also studied extensively. However, the
location prediction problem from twitter depends highly on tweet content. Users living
in specific regions, locations may examine neighborhood tourist spots, landmarks and
buildings and related events.

Excellence and Service


Christ University

Home Location: User’s residential address given by user or location given by


user on account creation is considered as home location. Home location
prediction can be used in various application namely recommendation systems,
location-based advertisements, health monitoring, and polling etc. Home
location can be specified as administrative location, geographical location or co-
ordinates. Tweet Location: Tweet location refers to the region from where the
tweet is posted by user. By construing tweet location, one can get tweet person’s
mobility.

Excellence and Service


Christ University

SYSTEM ARCHITECTURE:

Excellence and Service


Christ University

DATA FLOW DIAGRAM:

Excellence and Service


Christ University

USE CASE DIAGRAM:

Excellence and Service


Christ University

SEQUENCE DIAGRAM:

Excellence and Service


Christ University

ACTIVITY DIAGRAM:

Excellence and Service


Christ University

MODULES

User
Admin
Data Preprocess
Machine Learning

Excellence and Service


Christ University

ADVANTAGES

1. The information extracted from live includes tweet-id, name,


screen_name, tweet_ text, Home Location, Tweet Location, Mentioned
Location.

2. Tweet text is compared with natural language tool kit package available
in python to extract data from Cursor to Pandas Data frame.

3. Python programming, with few libraries used are scikit learn, NumPy,
pandas and geography

Excellence and Service


Christ University

DISADVANTAGES
1.The issue of location prediction related named as geolocation prediction
is examined for Wikipedia and web page documents.

2. Entity recognition from these formal documents has been researched for
years.

3. The location prediction problem from twitter depends highly on tweet


content.

Excellence and Service


Christ University

CONCLUSION

Three locations are considered from twitter data, namely home location,
mentioned location and tweet location. When the twitter data is considered,
geolocation prediction becomes a challenging problem. The tweet text nature and
number of characters limitation make it hard to understand and analyze. In this
work, we have predicted the geolocation of user from their tweet text using
machine learning algorithms. We have implemented three algorithms to show the
better performed one, which is suitable for geolocation prediction problem. Our
experiment analysis concluded that decision tree is suitable for tweet text analysis
and location prediction problem.

Excellence and Service


Christ University

References
[1] Han, Bo & Cook, Paul & Baldwin, Timothy. (2012). Geolocation Prediction in
Social Media Data by Finding Location Indicative Words. 24th International
Conference on Computational Linguistics - Proceedings of COLING 2012:
Technical Papers. 1045-1062.
[2] Ren K., Zhang S., Lin H. (2012) Where Are You Settling Down: Geo-locating
Twitter Users Based on Tweets and Social Networks. In: Hou Y., Nie JY., Sun L.,
Wang B., Zhang P. (eds) Information Retrieval Technology. AIRS 2012. Lecture
Notes in Computer Science, vol 7675. Springer, Berlin, Heidelberg.
[3] Han, Bo & Cook, Paul & Baldwin, Timothy. (2014). Text-Based Twitter User
Geolocation Prediction. The Journal of Artificial Intelligence Research (JAIR). 49.
10.1613/jair.4200.
[4] Li, Rui & Wang, Shengjie & Chen-Chuan Chang, Kevin. (2012). Multiple
Location Profiling for Users and Relationships from Social Network and Content.
Proceedings of the VLDB Endowment. 5. 10.14778/2350229.2350273.

Excellence and Service


Christ University

Excellence and Service

You might also like