Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter
International audience The prediction of bursty events on the Internet is a challenging task. Difficulties are due to the diversity of information sources, the size of the Internet, dynamics of popularity, user behaviors. . On the other hand, Twitter is a structured and limited space. In this paper,...
Main Authors: | , , |
---|---|
Other Authors: | , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2014
|
Subjects: | |
Online Access: | https://hal.archives-ouvertes.fr/hal-01319806 |
id |
ftunivavignon:oai:HAL:hal-01319806v1 |
---|---|
record_format |
openpolar |
spelling |
ftunivavignon:oai:HAL:hal-01319806v1 2023-05-15T16:49:47+02:00 Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter Morchid, Mohamed Linarès, Georges Dufour, Richard Laboratoire Informatique d'Avignon (LIA) Avignon Université (AU)-Centre d'Enseignement et de Recherche en Informatique - CERI Reykjavik, Iceland 2014-05 https://hal.archives-ouvertes.fr/hal-01319806 en eng HAL CCSD hal-01319806 https://hal.archives-ouvertes.fr/hal-01319806 LREC https://hal.archives-ouvertes.fr/hal-01319806 LREC, May 2014, Reykjavik, Iceland Bursty events detection Latent Dirichlet Allocation Neural network [INFO]Computer Science [cs] info:eu-repo/semantics/conferenceObject Conference papers 2014 ftunivavignon 2022-10-18T08:11:35Z International audience The prediction of bursty events on the Internet is a challenging task. Difficulties are due to the diversity of information sources, the size of the Internet, dynamics of popularity, user behaviors. . On the other hand, Twitter is a structured and limited space. In this paper, we present a new method for predicting bursty events using content-related indices. Prediction is performed by a neural network that combines three features in order to predict the number of retweets of a tweet on the Twitter platform. The indices are related to popularity, expressivity and singularity. Popularity index is based on the analysis of RSS streams. Expressivity uses a dictionary that contains words annotated in terms of expressivity load. Singularity represents outlying topic association estimated via a Latent Dirichlet Allocation (LDA) model. Experiments demonstrate the effectiveness of the proposal with a 72% F-measure prediction score for the tweets that have been forwarded at least 60 times. Conference Object Iceland Université d'Avignon et des Pays de Vaucluse: HAL |
institution |
Open Polar |
collection |
Université d'Avignon et des Pays de Vaucluse: HAL |
op_collection_id |
ftunivavignon |
language |
English |
topic |
Bursty events detection Latent Dirichlet Allocation Neural network [INFO]Computer Science [cs] |
spellingShingle |
Bursty events detection Latent Dirichlet Allocation Neural network [INFO]Computer Science [cs] Morchid, Mohamed Linarès, Georges Dufour, Richard Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter |
topic_facet |
Bursty events detection Latent Dirichlet Allocation Neural network [INFO]Computer Science [cs] |
description |
International audience The prediction of bursty events on the Internet is a challenging task. Difficulties are due to the diversity of information sources, the size of the Internet, dynamics of popularity, user behaviors. . On the other hand, Twitter is a structured and limited space. In this paper, we present a new method for predicting bursty events using content-related indices. Prediction is performed by a neural network that combines three features in order to predict the number of retweets of a tweet on the Twitter platform. The indices are related to popularity, expressivity and singularity. Popularity index is based on the analysis of RSS streams. Expressivity uses a dictionary that contains words annotated in terms of expressivity load. Singularity represents outlying topic association estimated via a Latent Dirichlet Allocation (LDA) model. Experiments demonstrate the effectiveness of the proposal with a 72% F-measure prediction score for the tweets that have been forwarded at least 60 times. |
author2 |
Laboratoire Informatique d'Avignon (LIA) Avignon Université (AU)-Centre d'Enseignement et de Recherche en Informatique - CERI |
format |
Conference Object |
author |
Morchid, Mohamed Linarès, Georges Dufour, Richard |
author_facet |
Morchid, Mohamed Linarès, Georges Dufour, Richard |
author_sort |
Morchid, Mohamed |
title |
Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter |
title_short |
Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter |
title_full |
Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter |
title_fullStr |
Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter |
title_full_unstemmed |
Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter |
title_sort |
characterizing and predicting bursty events: the buzz case study on twitter |
publisher |
HAL CCSD |
publishDate |
2014 |
url |
https://hal.archives-ouvertes.fr/hal-01319806 |
op_coverage |
Reykjavik, Iceland |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
LREC https://hal.archives-ouvertes.fr/hal-01319806 LREC, May 2014, Reykjavik, Iceland |
op_relation |
hal-01319806 https://hal.archives-ouvertes.fr/hal-01319806 |
_version_ |
1766039967757238272 |