Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications

Ketaki Gandhe, Aparna Varde, Xu Du

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a sentiment analysis approach to extract sentiments of tweets based on their polarity and subjectivity, classify them and visualize results graphically. This helps to understand opinions of existing users that can be helpful in future recommendations. Our proposed approach entails a hybrid learning method for classification of tweets based on a Bayesian probabilistic method for sentence level models given partially labeled training data. For implementation, we use AWS to extract data from Twitter, store extracted data in MySQL databases and code Python scripts in order to implement the analyzer. The graphical models are viewed using IPython Notebook. The results of this work would be helpful in providing recommendations to users for product reviews, political campaigns, stock predictions, urban policy decisions etc. The novelty of this research lies mainly in the hybrid learning method for sentiment analysis. We present our approach along with its implementation, evaluation and applications.

Original languageEnglish
Title of host publication2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018
EditorsSatyajit Chakrabarti, Himadri Nath Saha
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages57-63
Number of pages7
ISBN (Electronic)9781538676936
DOIs
StatePublished - 1 Nov 2018
Event9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018 - New York City, United States
Duration: 8 Nov 201810 Nov 2018

Publication series

Name2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018

Conference

Conference9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018
CountryUnited States
CityNew York City
Period8/11/1810/11/18

Fingerprint

recommendations
learning
sentences
analyzers
polarity
education
evaluation
products
predictions

Keywords

  • Data Analytics
  • Hybrid Learning
  • Opinion Mining
  • Recommenders
  • Social Media
  • Twitter
  • Urban Policy

Cite this

Gandhe, K., Varde, A., & Du, X. (2018). Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications. In S. Chakrabarti, & H. N. Saha (Eds.), 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018 (pp. 57-63). [8796661] (2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UEMCON.2018.8796661
Gandhe, Ketaki ; Varde, Aparna ; Du, Xu. / Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications. 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018. editor / Satyajit Chakrabarti ; Himadri Nath Saha. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 57-63 (2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018).
@inproceedings{95340518785c485fb0ce5e863c33b593,
title = "Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications",
abstract = "This paper proposes a sentiment analysis approach to extract sentiments of tweets based on their polarity and subjectivity, classify them and visualize results graphically. This helps to understand opinions of existing users that can be helpful in future recommendations. Our proposed approach entails a hybrid learning method for classification of tweets based on a Bayesian probabilistic method for sentence level models given partially labeled training data. For implementation, we use AWS to extract data from Twitter, store extracted data in MySQL databases and code Python scripts in order to implement the analyzer. The graphical models are viewed using IPython Notebook. The results of this work would be helpful in providing recommendations to users for product reviews, political campaigns, stock predictions, urban policy decisions etc. The novelty of this research lies mainly in the hybrid learning method for sentiment analysis. We present our approach along with its implementation, evaluation and applications.",
keywords = "Data Analytics, Hybrid Learning, Opinion Mining, Recommenders, Social Media, Twitter, Urban Policy",
author = "Ketaki Gandhe and Aparna Varde and Xu Du",
year = "2018",
month = "11",
day = "1",
doi = "10.1109/UEMCON.2018.8796661",
language = "English",
series = "2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "57--63",
editor = "Satyajit Chakrabarti and Saha, {Himadri Nath}",
booktitle = "2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018",

}

Gandhe, K, Varde, A & Du, X 2018, Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications. in S Chakrabarti & HN Saha (eds), 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018., 8796661, 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018, Institute of Electrical and Electronics Engineers Inc., pp. 57-63, 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018, New York City, United States, 8/11/18. https://doi.org/10.1109/UEMCON.2018.8796661

Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications. / Gandhe, Ketaki; Varde, Aparna; Du, Xu.

2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018. ed. / Satyajit Chakrabarti; Himadri Nath Saha. Institute of Electrical and Electronics Engineers Inc., 2018. p. 57-63 8796661 (2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications

AU - Gandhe, Ketaki

AU - Varde, Aparna

AU - Du, Xu

PY - 2018/11/1

Y1 - 2018/11/1

N2 - This paper proposes a sentiment analysis approach to extract sentiments of tweets based on their polarity and subjectivity, classify them and visualize results graphically. This helps to understand opinions of existing users that can be helpful in future recommendations. Our proposed approach entails a hybrid learning method for classification of tweets based on a Bayesian probabilistic method for sentence level models given partially labeled training data. For implementation, we use AWS to extract data from Twitter, store extracted data in MySQL databases and code Python scripts in order to implement the analyzer. The graphical models are viewed using IPython Notebook. The results of this work would be helpful in providing recommendations to users for product reviews, political campaigns, stock predictions, urban policy decisions etc. The novelty of this research lies mainly in the hybrid learning method for sentiment analysis. We present our approach along with its implementation, evaluation and applications.

AB - This paper proposes a sentiment analysis approach to extract sentiments of tweets based on their polarity and subjectivity, classify them and visualize results graphically. This helps to understand opinions of existing users that can be helpful in future recommendations. Our proposed approach entails a hybrid learning method for classification of tweets based on a Bayesian probabilistic method for sentence level models given partially labeled training data. For implementation, we use AWS to extract data from Twitter, store extracted data in MySQL databases and code Python scripts in order to implement the analyzer. The graphical models are viewed using IPython Notebook. The results of this work would be helpful in providing recommendations to users for product reviews, political campaigns, stock predictions, urban policy decisions etc. The novelty of this research lies mainly in the hybrid learning method for sentiment analysis. We present our approach along with its implementation, evaluation and applications.

KW - Data Analytics

KW - Hybrid Learning

KW - Opinion Mining

KW - Recommenders

KW - Social Media

KW - Twitter

KW - Urban Policy

UR - http://www.scopus.com/inward/record.url?scp=85071577144&partnerID=8YFLogxK

U2 - 10.1109/UEMCON.2018.8796661

DO - 10.1109/UEMCON.2018.8796661

M3 - Conference contribution

AN - SCOPUS:85071577144

T3 - 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018

SP - 57

EP - 63

BT - 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018

A2 - Chakrabarti, Satyajit

A2 - Saha, Himadri Nath

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Gandhe K, Varde A, Du X. Sentiment Analysis of Twitter Data with Hybrid Learning for Recommender Applications. In Chakrabarti S, Saha HN, editors, 2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 57-63. 8796661. (2018 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2018). https://doi.org/10.1109/UEMCON.2018.8796661