Real-Time Detection of Twitter Social Events from the User's Perspective

Risultato della ricerca: Conference contribution

15 Citazioni (Scopus)

Abstract

Over the last 40 years, automatic solutions to analyze text documents collection have been one of the most attractive challenges in the field of information retrieval. More recently, the focus has moved towards dynamic, distributed environments, where documents are continuously created by the users of a virtual community, i.e., the social network. In the case of Twitter, such documents, called tweets, are usually related to events which involve many people in different parts of the world. In this work we present a system for real-time Twitter data analysis which allows to follow a generic event from the user's point of view. The topic detection algorithm we propose is an improved version of the Soft Frequent Pattern Mining algorithm, designed to deal with dynamic environments. In particular, in order to obtain prompt results, the whole Twitter stream is split in dynamic windows whose size depends both on the volume of tweets and time. Moreover, the set of terms we use to query Twitter is progressively refined to include new relevant keywords which point out the emergence of new subtopics or new trends in the main topic. Tests have been performed to evaluate the performance of the framework and experimental results show the effectiveness of our solution.
Lingua originaleEnglish
Titolo della pubblicazione ospite2015 IEEE International Conference on Communications (ICC)
Pagine1207-1212
Numero di pagine6
Stato di pubblicazionePublished - 2015

Serie di pubblicazioni

NomeIEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS

Fingerprint

Information retrieval

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cita questo

Morana, M., Lo Re, G., Gaglio, S., & Gaglio, S. (2015). Real-Time Detection of Twitter Social Events from the User's Perspective. In 2015 IEEE International Conference on Communications (ICC) (pagg. 1207-1212). (IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS).

Real-Time Detection of Twitter Social Events from the User's Perspective. / Morana, Marco; Lo Re, Giuseppe; Gaglio, Salvatore; Gaglio, Salvatore.

2015 IEEE International Conference on Communications (ICC). 2015. pag. 1207-1212 (IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS).

Risultato della ricerca: Conference contribution

Morana, M, Lo Re, G, Gaglio, S & Gaglio, S 2015, Real-Time Detection of Twitter Social Events from the User's Perspective. in 2015 IEEE International Conference on Communications (ICC). IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, pagg. 1207-1212.
Morana M, Lo Re G, Gaglio S, Gaglio S. Real-Time Detection of Twitter Social Events from the User's Perspective. In 2015 IEEE International Conference on Communications (ICC). 2015. pag. 1207-1212. (IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS).
Morana, Marco ; Lo Re, Giuseppe ; Gaglio, Salvatore ; Gaglio, Salvatore. / Real-Time Detection of Twitter Social Events from the User's Perspective. 2015 IEEE International Conference on Communications (ICC). 2015. pagg. 1207-1212 (IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS).
@inproceedings{9cd6537166bc43dfa09e95c4c9d87109,
title = "Real-Time Detection of Twitter Social Events from the User's Perspective",
abstract = "Over the last 40 years, automatic solutions to analyze text documents collection have been one of the most attractive challenges in the field of information retrieval. More recently, the focus has moved towards dynamic, distributed environments, where documents are continuously created by the users of a virtual community, i.e., the social network. In the case of Twitter, such documents, called tweets, are usually related to events which involve many people in different parts of the world. In this work we present a system for real-time Twitter data analysis which allows to follow a generic event from the user's point of view. The topic detection algorithm we propose is an improved version of the Soft Frequent Pattern Mining algorithm, designed to deal with dynamic environments. In particular, in order to obtain prompt results, the whole Twitter stream is split in dynamic windows whose size depends both on the volume of tweets and time. Moreover, the set of terms we use to query Twitter is progressively refined to include new relevant keywords which point out the emergence of new subtopics or new trends in the main topic. Tests have been performed to evaluate the performance of the framework and experimental results show the effectiveness of our solution.",
author = "Marco Morana and {Lo Re}, Giuseppe and Salvatore Gaglio and Salvatore Gaglio",
year = "2015",
language = "English",
isbn = "9781467364324",
series = "IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS",
pages = "1207--1212",
booktitle = "2015 IEEE International Conference on Communications (ICC)",

}

TY - GEN

T1 - Real-Time Detection of Twitter Social Events from the User's Perspective

AU - Morana, Marco

AU - Lo Re, Giuseppe

AU - Gaglio, Salvatore

AU - Gaglio, Salvatore

PY - 2015

Y1 - 2015

N2 - Over the last 40 years, automatic solutions to analyze text documents collection have been one of the most attractive challenges in the field of information retrieval. More recently, the focus has moved towards dynamic, distributed environments, where documents are continuously created by the users of a virtual community, i.e., the social network. In the case of Twitter, such documents, called tweets, are usually related to events which involve many people in different parts of the world. In this work we present a system for real-time Twitter data analysis which allows to follow a generic event from the user's point of view. The topic detection algorithm we propose is an improved version of the Soft Frequent Pattern Mining algorithm, designed to deal with dynamic environments. In particular, in order to obtain prompt results, the whole Twitter stream is split in dynamic windows whose size depends both on the volume of tweets and time. Moreover, the set of terms we use to query Twitter is progressively refined to include new relevant keywords which point out the emergence of new subtopics or new trends in the main topic. Tests have been performed to evaluate the performance of the framework and experimental results show the effectiveness of our solution.

AB - Over the last 40 years, automatic solutions to analyze text documents collection have been one of the most attractive challenges in the field of information retrieval. More recently, the focus has moved towards dynamic, distributed environments, where documents are continuously created by the users of a virtual community, i.e., the social network. In the case of Twitter, such documents, called tweets, are usually related to events which involve many people in different parts of the world. In this work we present a system for real-time Twitter data analysis which allows to follow a generic event from the user's point of view. The topic detection algorithm we propose is an improved version of the Soft Frequent Pattern Mining algorithm, designed to deal with dynamic environments. In particular, in order to obtain prompt results, the whole Twitter stream is split in dynamic windows whose size depends both on the volume of tweets and time. Moreover, the set of terms we use to query Twitter is progressively refined to include new relevant keywords which point out the emergence of new subtopics or new trends in the main topic. Tests have been performed to evaluate the performance of the framework and experimental results show the effectiveness of our solution.

UR - http://hdl.handle.net/10447/151877

M3 - Conference contribution

SN - 9781467364324

T3 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS

SP - 1207

EP - 1212

BT - 2015 IEEE International Conference on Communications (ICC)

ER -