Cross domain sentiment analysis using transfer learning

Bharat Gupta; Shivam Awasthi; Parshant Singh; Likhama Ram; Pramod Kumar; Bakshi Rohit Prasad; Sonali Agarwal

doi:10.1109/ICIINFS.2017.8300363

Cross domain sentiment analysis using transfer learning

Bharat Gupta, Shivam Awasthi, Parshant Singh, Likhama Ram, Pramod Kumar, Bakshi Rohit Prasad, Sonali Agarwal

Indian Institute of Information Technology, Allahabad

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Transfer learning is an emerging research area which extracts knowledge from one or more than one source domains and utilizes this gained knowledge to perform some task in a target domain. It has emerged as a popular topic in recent years, because this technique is considered to be helpful in reducing the cost of labeling. It has many applications on different domains such as Natural Language Processing, Image and Video Processing, etc. The aim is to study transfer learning and implement it for Sentiment Analysis of Tweets by using the knowledge of Yelp reviews. We find that transfer Learning approach is faster than the conventional machine learning approach and give comparable accuracy at much smaller dataset.

Original language	English
Title of host publication	2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781538616741
DOIs	https://doi.org/10.1109/ICIINFS.2017.8300363
State	Published - 2 Jul 2017
Externally published	Yes
Event	12th IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Peradeniya, Sri Lanka Duration: 15 Dec 2017 → 16 Dec 2017

Publication series

Name	2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings
Volume	2018-January

Conference

Conference	12th IEEE International Conference on Industrial and Information Systems, ICIIS 2017
Country/Territory	Sri Lanka
City	Peradeniya
Period	15/12/17 → 16/12/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

Transfer Learning
Twitter
Yelp reviews
knowledge transfer
sentiment analysis

Access to Document

10.1109/ICIINFS.2017.8300363

Cite this

Gupta, B., Awasthi, S., Singh, P., Ram, L., Kumar, P., Prasad, B. R., & Agarwal, S. (2017). Cross domain sentiment analysis using transfer learning. In 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings (pp. 1-5). (2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIINFS.2017.8300363

Gupta, Bharat ; Awasthi, Shivam ; Singh, Parshant et al. / Cross domain sentiment analysis using transfer learning. 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-5 (2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings).

@inproceedings{b5101ebf16034fabbde6cdced8e70163,

title = "Cross domain sentiment analysis using transfer learning",

abstract = "Transfer learning is an emerging research area which extracts knowledge from one or more than one source domains and utilizes this gained knowledge to perform some task in a target domain. It has emerged as a popular topic in recent years, because this technique is considered to be helpful in reducing the cost of labeling. It has many applications on different domains such as Natural Language Processing, Image and Video Processing, etc. The aim is to study transfer learning and implement it for Sentiment Analysis of Tweets by using the knowledge of Yelp reviews. We find that transfer Learning approach is faster than the conventional machine learning approach and give comparable accuracy at much smaller dataset.",

keywords = "Transfer Learning, Twitter, Yelp reviews, knowledge transfer, sentiment analysis",

author = "Bharat Gupta and Shivam Awasthi and Parshant Singh and Likhama Ram and Pramod Kumar and Prasad, {Bakshi Rohit} and Sonali Agarwal",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 12th IEEE International Conference on Industrial and Information Systems, ICIIS 2017 ; Conference date: 15-12-2017 Through 16-12-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICIINFS.2017.8300363",

language = "אנגלית",

series = "2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--5",

booktitle = "2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings",

address = "ארצות הברית",

}

Gupta, B, Awasthi, S, Singh, P, Ram, L, Kumar, P, Prasad, BR & Agarwal, S 2017, Cross domain sentiment analysis using transfer learning. in 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings. 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 12th IEEE International Conference on Industrial and Information Systems, ICIIS 2017, Peradeniya, Sri Lanka, 15/12/17. https://doi.org/10.1109/ICIINFS.2017.8300363

Cross domain sentiment analysis using transfer learning. / Gupta, Bharat; Awasthi, Shivam; Singh, Parshant et al.
2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-5 (2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings; Vol. 2018-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Cross domain sentiment analysis using transfer learning

AU - Gupta, Bharat

AU - Awasthi, Shivam

AU - Singh, Parshant

AU - Ram, Likhama

AU - Kumar, Pramod

AU - Prasad, Bakshi Rohit

AU - Agarwal, Sonali

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Transfer learning is an emerging research area which extracts knowledge from one or more than one source domains and utilizes this gained knowledge to perform some task in a target domain. It has emerged as a popular topic in recent years, because this technique is considered to be helpful in reducing the cost of labeling. It has many applications on different domains such as Natural Language Processing, Image and Video Processing, etc. The aim is to study transfer learning and implement it for Sentiment Analysis of Tweets by using the knowledge of Yelp reviews. We find that transfer Learning approach is faster than the conventional machine learning approach and give comparable accuracy at much smaller dataset.

AB - Transfer learning is an emerging research area which extracts knowledge from one or more than one source domains and utilizes this gained knowledge to perform some task in a target domain. It has emerged as a popular topic in recent years, because this technique is considered to be helpful in reducing the cost of labeling. It has many applications on different domains such as Natural Language Processing, Image and Video Processing, etc. The aim is to study transfer learning and implement it for Sentiment Analysis of Tweets by using the knowledge of Yelp reviews. We find that transfer Learning approach is faster than the conventional machine learning approach and give comparable accuracy at much smaller dataset.

KW - Transfer Learning

KW - Twitter

KW - Yelp reviews

KW - knowledge transfer

KW - sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=85050519676&partnerID=8YFLogxK

U2 - 10.1109/ICIINFS.2017.8300363

DO - 10.1109/ICIINFS.2017.8300363

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85050519676

T3 - 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings

SP - 1

EP - 5

BT - 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Conference on Industrial and Information Systems, ICIIS 2017

Y2 - 15 December 2017 through 16 December 2017

ER -

Gupta B, Awasthi S, Singh P, Ram L, Kumar P, Prasad BR et al. Cross domain sentiment analysis using transfer learning. In 2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-5. (2017 IEEE International Conference on Industrial and Information Systems, ICIIS 2017 - Proceedings). doi: 10.1109/ICIINFS.2017.8300363

Cross domain sentiment analysis using transfer learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this