User's Location prediction from Tweets using Ensemble machine learning models
Social media, Tweets, location prediction, Machine Learning, Random Forest (RF), Bagging model, Extra Trees (ET), Natural Language Processing (NLP), Term Frequency-Inverse Document Frequency (TF-IDF)
On-time and accurate detection of user's home location is a challenging task; however automated detection of location can be used more effectively in applications such as disaster response and public health. Large user-base nature of social media such as twitter makes the application more viable than traditional user-base data like census data. Twitter has been considered as one of the most powerful social media sites due to its worldwide inclusion of users and continuous stream of message from its users. As these tweets are very short text and noisy, identifying the user's location information is quite challenging. To overcome this issue, location information of user's is extracted through geography data. In this proposed framework, the detailed outline of location prediction using tweet text is studied by extraction of location information from user's tweets and user's location and is predicted through their tweet texts. The Natural Language Processing (NLP) technique, Term Frequency-Inverse Document Frequency (TF-IDF) is used for feature extraction from tweets. In this paper, to improve the accuracy of prediction than traditional models, we predict the user's location based on extracted features from tweets using ensemble machine learning models namely Random Forest (RF), Bagging model and Extra Trees model. Experimental results showed that Bagging Classifier (with based model Decision Tree) has achieved the highest accuracy of 99.82% for user's location prediction.
"User's Location prediction from Tweets using Ensemble machine learning models", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.9, Issue 10, page no.a717-a722, October-2024, Available :https://ijnrd.org/papers/IJNRD2410074.pdf
Volume 9
Issue 10,
October-2024
Pages : a717-a722
Paper Reg. ID: IJNRD_301122
Published Paper Id: IJNRD2410074
Downloads: 00036
Research Area: Science and Technology
Country: Gurugram, Haryana, India
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
