Mining twitter features for event summarization and rating

Deepa Mallela; Dirk Ahlers; Maria Soledad Pera

doi:10.1145/3106426.3106487

Mining twitter features for event summarization and rating

Deepa Mallela, Dirk Ahlers, Maria Soledad Pera

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

7 Citations (Scopus)

Abstract

We present CEST, a generic method for detection and rich summarization of events occurring in a city. CEST exploits Twitter metadata, does not need prior information on events, and is event category and structure agnostic. We developed CEST to process unstructured documents and take advantage of shorthand notations, hashtags, keywords, geographical and temporal data, as well as sentiment within tweets to both detect and summarize arbitrary events without prior knowledge. We also introduce a novel strategy that analyzes sentiment and tweeting behavior over time to create a qualitative score that captures events' overall appeal to attendees.

Original language	English
Title of host publication	Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
Publisher	ACM
Pages	615-622
Number of pages	8
ISBN (Electronic)	9781450349512
DOIs	https://doi.org/10.1145/3106426.3106487
Publication status	Published - 23 Aug 2017
Externally published	Yes
Event	16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017 - Leipzig, Germany Duration: 23 Aug 2017 → 26 Aug 2017

Conference

Conference	16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
Country/Territory	Germany
City	Leipzig
Period	23/08/17 → 26/08/17

Keywords

Event
Spatio-Temporal analysis
Summarization
Twitter

Access to Document

10.1145/3106426.3106487

Cite this

@inproceedings{cfbbf56c89e24915b21167e2a2f62444,

title = "Mining twitter features for event summarization and rating",

abstract = "We present CEST, a generic method for detection and rich summarization of events occurring in a city. CEST exploits Twitter metadata, does not need prior information on events, and is event category and structure agnostic. We developed CEST to process unstructured documents and take advantage of shorthand notations, hashtags, keywords, geographical and temporal data, as well as sentiment within tweets to both detect and summarize arbitrary events without prior knowledge. We also introduce a novel strategy that analyzes sentiment and tweeting behavior over time to create a qualitative score that captures events' overall appeal to attendees.",

keywords = "Event, Spatio-Temporal analysis, Summarization, Twitter",

author = "Deepa Mallela and Dirk Ahlers and Pera, {Maria Soledad}",

year = "2017",

month = aug,

day = "23",

doi = "10.1145/3106426.3106487",

language = "English",

pages = "615--622",

booktitle = "Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017",

publisher = "ACM",

address = "United States",

note = "16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017 ; Conference date: 23-08-2017 Through 26-08-2017",

}

TY - GEN

T1 - Mining twitter features for event summarization and rating

AU - Mallela, Deepa

AU - Ahlers, Dirk

AU - Pera, Maria Soledad

PY - 2017/8/23

Y1 - 2017/8/23

N2 - We present CEST, a generic method for detection and rich summarization of events occurring in a city. CEST exploits Twitter metadata, does not need prior information on events, and is event category and structure agnostic. We developed CEST to process unstructured documents and take advantage of shorthand notations, hashtags, keywords, geographical and temporal data, as well as sentiment within tweets to both detect and summarize arbitrary events without prior knowledge. We also introduce a novel strategy that analyzes sentiment and tweeting behavior over time to create a qualitative score that captures events' overall appeal to attendees.

AB - We present CEST, a generic method for detection and rich summarization of events occurring in a city. CEST exploits Twitter metadata, does not need prior information on events, and is event category and structure agnostic. We developed CEST to process unstructured documents and take advantage of shorthand notations, hashtags, keywords, geographical and temporal data, as well as sentiment within tweets to both detect and summarize arbitrary events without prior knowledge. We also introduce a novel strategy that analyzes sentiment and tweeting behavior over time to create a qualitative score that captures events' overall appeal to attendees.

KW - Event

KW - Spatio-Temporal analysis

KW - Summarization

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85031037754&partnerID=8YFLogxK

U2 - 10.1145/3106426.3106487

DO - 10.1145/3106426.3106487

M3 - Conference contribution

AN - SCOPUS:85031037754

SP - 615

EP - 622

BT - Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017

PB - ACM

T2 - 16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017

Y2 - 23 August 2017 through 26 August 2017

ER -

Mining twitter features for event summarization and rating

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this