Context based interesting tweet recommendation framework

Maulik Dang, Sanjay Singh

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

Abstract

Social media such as Twitter, Google+, Facebook, etc has an undeniable effect on the way information is stored and processed by us. The information available on the web is abound and hence it is essential to mine the important information and avoid the irrelevant details. Along with this, it is beneficial to consider information that is contextually similar to information related to a particular topic as it provides a big picture. Tweets contains keywords known as hashtags which provide useful information for the purpose of sentiment analysis, named entity recognition, event detection, etc. In this paper, we have analyzed Twitter data based on their hashtags, which is widely used nowadays. We have extracted tweets pertaining to a single keyword and to contextually similar keywords. For the purpose of finding similar words we have used word embeddings that capture contextual information successfully. We have used topic modeling to expose the latent structure of the documents based on probability distribution. The proposed framework helps user to find relevant tweets pertaining to a specific and to contextually similar hashtags.

Original languageEnglish
Title of host publication2016 IEEE Annual India Conference, INDICON 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509036462
DOIs
Publication statusPublished - 31-01-2017
Event2016 IEEE Annual India Conference, INDICON 2016 - Bangalore, India
Duration: 16-12-201618-12-2016

Conference

Conference2016 IEEE Annual India Conference, INDICON 2016
CountryIndia
CityBangalore
Period16-12-1618-12-16

Fingerprint

recommendations
Probability distributions
embedding

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Networks and Communications
  • Instrumentation

Cite this

Dang, M., & Singh, S. (2017). Context based interesting tweet recommendation framework. In 2016 IEEE Annual India Conference, INDICON 2016 [7838957] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INDICON.2016.7838957
Dang, Maulik ; Singh, Sanjay. / Context based interesting tweet recommendation framework. 2016 IEEE Annual India Conference, INDICON 2016. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{de647928a9084d33b1df140dda1eeddf,
title = "Context based interesting tweet recommendation framework",
abstract = "Social media such as Twitter, Google+, Facebook, etc has an undeniable effect on the way information is stored and processed by us. The information available on the web is abound and hence it is essential to mine the important information and avoid the irrelevant details. Along with this, it is beneficial to consider information that is contextually similar to information related to a particular topic as it provides a big picture. Tweets contains keywords known as hashtags which provide useful information for the purpose of sentiment analysis, named entity recognition, event detection, etc. In this paper, we have analyzed Twitter data based on their hashtags, which is widely used nowadays. We have extracted tweets pertaining to a single keyword and to contextually similar keywords. For the purpose of finding similar words we have used word embeddings that capture contextual information successfully. We have used topic modeling to expose the latent structure of the documents based on probability distribution. The proposed framework helps user to find relevant tweets pertaining to a specific and to contextually similar hashtags.",
author = "Maulik Dang and Sanjay Singh",
year = "2017",
month = "1",
day = "31",
doi = "10.1109/INDICON.2016.7838957",
language = "English",
booktitle = "2016 IEEE Annual India Conference, INDICON 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Dang, M & Singh, S 2017, Context based interesting tweet recommendation framework. in 2016 IEEE Annual India Conference, INDICON 2016., 7838957, Institute of Electrical and Electronics Engineers Inc., 2016 IEEE Annual India Conference, INDICON 2016, Bangalore, India, 16-12-16. https://doi.org/10.1109/INDICON.2016.7838957

Context based interesting tweet recommendation framework. / Dang, Maulik; Singh, Sanjay.

2016 IEEE Annual India Conference, INDICON 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7838957.

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

TY - GEN

T1 - Context based interesting tweet recommendation framework

AU - Dang, Maulik

AU - Singh, Sanjay

PY - 2017/1/31

Y1 - 2017/1/31

N2 - Social media such as Twitter, Google+, Facebook, etc has an undeniable effect on the way information is stored and processed by us. The information available on the web is abound and hence it is essential to mine the important information and avoid the irrelevant details. Along with this, it is beneficial to consider information that is contextually similar to information related to a particular topic as it provides a big picture. Tweets contains keywords known as hashtags which provide useful information for the purpose of sentiment analysis, named entity recognition, event detection, etc. In this paper, we have analyzed Twitter data based on their hashtags, which is widely used nowadays. We have extracted tweets pertaining to a single keyword and to contextually similar keywords. For the purpose of finding similar words we have used word embeddings that capture contextual information successfully. We have used topic modeling to expose the latent structure of the documents based on probability distribution. The proposed framework helps user to find relevant tweets pertaining to a specific and to contextually similar hashtags.

AB - Social media such as Twitter, Google+, Facebook, etc has an undeniable effect on the way information is stored and processed by us. The information available on the web is abound and hence it is essential to mine the important information and avoid the irrelevant details. Along with this, it is beneficial to consider information that is contextually similar to information related to a particular topic as it provides a big picture. Tweets contains keywords known as hashtags which provide useful information for the purpose of sentiment analysis, named entity recognition, event detection, etc. In this paper, we have analyzed Twitter data based on their hashtags, which is widely used nowadays. We have extracted tweets pertaining to a single keyword and to contextually similar keywords. For the purpose of finding similar words we have used word embeddings that capture contextual information successfully. We have used topic modeling to expose the latent structure of the documents based on probability distribution. The proposed framework helps user to find relevant tweets pertaining to a specific and to contextually similar hashtags.

UR - http://www.scopus.com/inward/record.url?scp=85015209959&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015209959&partnerID=8YFLogxK

U2 - 10.1109/INDICON.2016.7838957

DO - 10.1109/INDICON.2016.7838957

M3 - Conference contribution

BT - 2016 IEEE Annual India Conference, INDICON 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Dang M, Singh S. Context based interesting tweet recommendation framework. In 2016 IEEE Annual India Conference, INDICON 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7838957 https://doi.org/10.1109/INDICON.2016.7838957