Extracting and modeling durations for habits and events from Twitter

Authors:
Jennifer Williams;Graham Katz
Affiliations:
Georgetown University, Washington, D.C.;Georgetown University, Washington, D.C.
Venue:
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2
Year:
2012

Citing 7
Cited 2

Temporal ontology and temporal reference

Computational Linguistics - Special issue on tense and aspect
Understanding the Yarowsky Algorithm

Computational Linguistics
NLTK: the natural language toolkit

ACLdemo '04 Proceedings of the ACL 2004 on Interactive poster and demonstration sessions
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
Using query patterns to learn the duration of events

IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
Learning Temporal Information for States and Events

ICSC '11 Proceedings of the 2011 IEEE Fifth International Conference on Semantic Computing
Annotating and learning event durations in text

Computational Linguistics

Extracting fine-grained durations for verbs from Twitter

ACL '12 Proceedings of ACL 2012 Student Research Workshop
Automatic dominant character identification in fables based on verb analysis - Empirical study on the impact of anaphora resolution

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We seek to automatically estimate typical durations for events and habits described in Twitter tweets. A corpus of more than 14 million tweets containing temporal duration information was collected. These tweets were classified as to their habituality status using a bootstrapped, decision tree. For each verb lemma, associated duration information was collected for episodic and habitual uses of the verb. Summary statistics for 483 verb lemmas and their typical habit and episode durations has been compiled and made available. This automatically generated duration information is broadly comparable to hand-annotation.