Real-world events discovering with TWIST

Natalia Vanetik; Marina Litvak; Efi Levi

doi:10.1007/978-3-030-52273-5_4

Real-world events discovering with TWIST

Natalia Vanetik, Marina Litvak, Efi Levi

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

1 Scopus citations

Abstract

Event detection in social media is a broad and well-addressed research topic, but the characteristics and sheer volume of Twitter messages with high amounts of noise in them make it a difficult task for Twitter. Tweets reporting real-life events are usually overwhelmed by a flood of meaningless information. This paper describes the TWItter event Summarizer and Trend detector (TWIST) system that attempts to tackle these challenges by combining wavelet and text analysis. TWIST extends the Event Detection with Clustering of Wavelet-based Signals (EDCoW) algorithm of Weng and Lee (ICWSM 11:401-408, 2011) with the use of text analysis of retrieved tweets. The system detects and summarizes real-life events reported in Twitter. TWIST analyses external sources for detected events to provide high-quality summaries with clean and meaningful content.

Original language	English
Title of host publication	Natural Language Processing for Electronic Design Automation
Publisher	Springer International Publishing
Pages	71-107
Number of pages	37
ISBN (Electronic)	9783030522735
ISBN (Print)	9783030522711
DOIs	https://doi.org/10.1007/978-3-030-52273-5_4
State	Published - 2 Oct 2020
Externally published	Yes

Keywords

Event detection
Summarization
Text analysis
Twitter
Wavelet analysis

ASJC Scopus subject areas

General Engineering

Access to Document

10.1007/978-3-030-52273-5_4

Cite this

@inbook{7075b61a161b4d2684d16492361bec81,

title = "Real-world events discovering with TWIST",

abstract = "Event detection in social media is a broad and well-addressed research topic, but the characteristics and sheer volume of Twitter messages with high amounts of noise in them make it a difficult task for Twitter. Tweets reporting real-life events are usually overwhelmed by a flood of meaningless information. This paper describes the TWItter event Summarizer and Trend detector (TWIST) system that attempts to tackle these challenges by combining wavelet and text analysis. TWIST extends the Event Detection with Clustering of Wavelet-based Signals (EDCoW) algorithm of Weng and Lee (ICWSM 11:401-408, 2011) with the use of text analysis of retrieved tweets. The system detects and summarizes real-life events reported in Twitter. TWIST analyses external sources for detected events to provide high-quality summaries with clean and meaningful content.",

keywords = "Event detection, Summarization, Text analysis, Twitter, Wavelet analysis",

author = "Natalia Vanetik and Marina Litvak and Efi Levi",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2020.",

year = "2020",

month = oct,

day = "2",

doi = "10.1007/978-3-030-52273-5_4",

language = "English",

isbn = "9783030522711",

pages = "71--107",

booktitle = "Natural Language Processing for Electronic Design Automation",

publisher = "Springer International Publishing",

}

TY - CHAP

T1 - Real-world events discovering with TWIST

AU - Vanetik, Natalia

AU - Litvak, Marina

AU - Levi, Efi

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2020.

PY - 2020/10/2

Y1 - 2020/10/2

N2 - Event detection in social media is a broad and well-addressed research topic, but the characteristics and sheer volume of Twitter messages with high amounts of noise in them make it a difficult task for Twitter. Tweets reporting real-life events are usually overwhelmed by a flood of meaningless information. This paper describes the TWItter event Summarizer and Trend detector (TWIST) system that attempts to tackle these challenges by combining wavelet and text analysis. TWIST extends the Event Detection with Clustering of Wavelet-based Signals (EDCoW) algorithm of Weng and Lee (ICWSM 11:401-408, 2011) with the use of text analysis of retrieved tweets. The system detects and summarizes real-life events reported in Twitter. TWIST analyses external sources for detected events to provide high-quality summaries with clean and meaningful content.

AB - Event detection in social media is a broad and well-addressed research topic, but the characteristics and sheer volume of Twitter messages with high amounts of noise in them make it a difficult task for Twitter. Tweets reporting real-life events are usually overwhelmed by a flood of meaningless information. This paper describes the TWItter event Summarizer and Trend detector (TWIST) system that attempts to tackle these challenges by combining wavelet and text analysis. TWIST extends the Event Detection with Clustering of Wavelet-based Signals (EDCoW) algorithm of Weng and Lee (ICWSM 11:401-408, 2011) with the use of text analysis of retrieved tweets. The system detects and summarizes real-life events reported in Twitter. TWIST analyses external sources for detected events to provide high-quality summaries with clean and meaningful content.

KW - Event detection

KW - Summarization

KW - Text analysis

KW - Twitter

KW - Wavelet analysis

UR - http://www.scopus.com/inward/record.url?scp=85148547904&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-52273-5_4

DO - 10.1007/978-3-030-52273-5_4

M3 - Chapter

AN - SCOPUS:85148547904

SN - 9783030522711

SP - 71

EP - 107

BT - Natural Language Processing for Electronic Design Automation

PB - Springer International Publishing

ER -

Real-world events discovering with TWIST

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this