Estimating time to event of future events based on linguistic cues on twitter

Ali Hürriyetoǧlu; Nelleke Oostdijk; Antal van den Bosch

doi:10.1007/978-3-319-67056-0_5

Estimating time to event of future events based on linguistic cues on twitter

Ali Hürriyetoǧlu, Nelleke Oostdijk, Antal van den Bosch

Meertens Institute

Research output: Chapter in book/volume › Chapter › Scientific › peer-review

Abstract

Given a stream of Twitter messages about an event, we investigate the predictive power of features generated from words and temporal expressions in the messages to estimate the time to event (TTE). From labeled training data average TTE values of the predictive features are learned, so that when they occur in an event-related tweet the TTE estimate can be provided for that tweet. We utilize temporal logic rules and a historical context integration function to improve the TTE estimation precision. In experiments on football matches and music concerts we show that the estimates of the method are off by 4 and 10 h in terms of mean absolute error on average, respectively. We find that the type and size of the event affect the estimation quality. An out-of-domain test on music concerts shows that models and hyperparameters trained and optimized on football matches can be used to estimate the remaining time to concerts. Moreover, mixing in concert events in training improves the precision of the average football event estimate.

Original language	English
Title of host publication	Studies in Computational Intelligence
Publisher	Springer Verlag GmbH
Pages	67-97
Number of pages	31
DOIs	https://doi.org/10.1007/978-3-319-67056-0_5
Publication status	Published - 2018

Publication series

Name	Studies in Computational Intelligence
Volume	740

Keywords

Football matches
Music concerts
Natural language processing
Skipgrams
Smart city
Social media analysis
Temporal expressions
Time-to-event estimation

Access to Document

10.1007/978-3-319-67056-0_5

Cite this

@inbook{d4ce73abe89645899ffc53362734c1c1,

title = "Estimating time to event of future events based on linguistic cues on twitter",

abstract = "Given a stream of Twitter messages about an event, we investigate the predictive power of features generated from words and temporal expressions in the messages to estimate the time to event (TTE). From labeled training data average TTE values of the predictive features are learned, so that when they occur in an event-related tweet the TTE estimate can be provided for that tweet. We utilize temporal logic rules and a historical context integration function to improve the TTE estimation precision. In experiments on football matches and music concerts we show that the estimates of the method are off by 4 and 10 h in terms of mean absolute error on average, respectively. We find that the type and size of the event affect the estimation quality. An out-of-domain test on music concerts shows that models and hyperparameters trained and optimized on football matches can be used to estimate the remaining time to concerts. Moreover, mixing in concert events in training improves the precision of the average football event estimate.",

keywords = "Football matches, Music concerts, Natural language processing, Skipgrams, Smart city, Social media analysis, Temporal expressions, Time-to-event estimation",

author = "Ali H{\"u}rriyetoǧlu and Nelleke Oostdijk and {van den Bosch}, Antal",

year = "2018",

doi = "10.1007/978-3-319-67056-0_5",

language = "English",

series = "Studies in Computational Intelligence",

publisher = "Springer Verlag GmbH",

pages = "67--97",

booktitle = "Studies in Computational Intelligence",

address = "Germany",

}

TY - CHAP

T1 - Estimating time to event of future events based on linguistic cues on twitter

AU - Hürriyetoǧlu, Ali

AU - Oostdijk, Nelleke

AU - van den Bosch, Antal

PY - 2018

Y1 - 2018

N2 - Given a stream of Twitter messages about an event, we investigate the predictive power of features generated from words and temporal expressions in the messages to estimate the time to event (TTE). From labeled training data average TTE values of the predictive features are learned, so that when they occur in an event-related tweet the TTE estimate can be provided for that tweet. We utilize temporal logic rules and a historical context integration function to improve the TTE estimation precision. In experiments on football matches and music concerts we show that the estimates of the method are off by 4 and 10 h in terms of mean absolute error on average, respectively. We find that the type and size of the event affect the estimation quality. An out-of-domain test on music concerts shows that models and hyperparameters trained and optimized on football matches can be used to estimate the remaining time to concerts. Moreover, mixing in concert events in training improves the precision of the average football event estimate.

AB - Given a stream of Twitter messages about an event, we investigate the predictive power of features generated from words and temporal expressions in the messages to estimate the time to event (TTE). From labeled training data average TTE values of the predictive features are learned, so that when they occur in an event-related tweet the TTE estimate can be provided for that tweet. We utilize temporal logic rules and a historical context integration function to improve the TTE estimation precision. In experiments on football matches and music concerts we show that the estimates of the method are off by 4 and 10 h in terms of mean absolute error on average, respectively. We find that the type and size of the event affect the estimation quality. An out-of-domain test on music concerts shows that models and hyperparameters trained and optimized on football matches can be used to estimate the remaining time to concerts. Moreover, mixing in concert events in training improves the precision of the average football event estimate.

KW - Football matches

KW - Music concerts

KW - Natural language processing

KW - Skipgrams

KW - Smart city

KW - Social media analysis

KW - Temporal expressions

KW - Time-to-event estimation

UR - https://www.mendeley.com/catalogue/f288b244-48d8-3c3d-ad00-2f5a2fccdfa2/

U2 - 10.1007/978-3-319-67056-0_5

DO - 10.1007/978-3-319-67056-0_5

M3 - Chapter

T3 - Studies in Computational Intelligence

SP - 67

EP - 97

BT - Studies in Computational Intelligence

PB - Springer Verlag GmbH

ER -

Estimating time to event of future events based on linguistic cues on twitter

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this