Querying Sentiment Development over Time

Troels Andreasen, Henning Christiansen, Christian Theil Have

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

A new language is introduced for describing hypotheses about fluctuations of measurable properties in streams of timestamped data, and as prime example, we consider trends of emotions in the constantly flowing stream of Twitter messages. The language, called EmoEpisodes, has a precise semantics that measures how well a hypothesis characterizes a given time interval; the semantics is parameterized so it can be adjusted to different views of the data. EmoEpisodes is extended to a query language with variables standing for unknown topics and emotions, and the query-answering mechanism will return instantiations for topics and emotions as well as time intervals that provide the largest deflections in this measurement. Experiments are performed on a selection of Twitter data to demonstrates the usefulness of the approach.
Original languageEnglish
Title of host publicationFlexible Query Answering Systems : 10th International Conference, FQAS 2013, Granada, Spain, September 18-20, 2013. Proceedings
Volume8132
Place of PublicationHeidelberg
PublisherSpringer
Publication date2013
Pages613-624
ISBN (Print)978-3-642-40768-0
Publication statusPublished - 2013
SeriesLecture notes in artificial intelligence
Volume8132
ISSN0302-9743

Cite this

Andreasen, T., Christiansen, H., & Have, C. T. (2013). Querying Sentiment Development over Time. In Flexible Query Answering Systems: 10th International Conference, FQAS 2013, Granada, Spain, September 18-20, 2013. Proceedings (Vol. 8132, pp. 613-624). Heidelberg: Springer. Lecture notes in artificial intelligence, Vol.. 8132
Andreasen, Troels ; Christiansen, Henning ; Have, Christian Theil. / Querying Sentiment Development over Time. Flexible Query Answering Systems: 10th International Conference, FQAS 2013, Granada, Spain, September 18-20, 2013. Proceedings. Vol. 8132 Heidelberg : Springer, 2013. pp. 613-624 (Lecture notes in artificial intelligence, Vol. 8132).
@inproceedings{4acf6a99237649f38e90a8934406965f,
title = "Querying Sentiment Development over Time",
abstract = "A new language is introduced for describing hypotheses about fluctuations of measurable properties in streams of timestamped data, and as prime example, we consider trends of emotions in the constantly flowing stream of Twitter messages. The language, called EmoEpisodes, has a precise semantics that measures how well a hypothesis characterizes a given time interval; the semantics is parameterized so it can be adjusted to different views of the data. EmoEpisodes is extended to a query language with variables standing for unknown topics and emotions, and the query-answering mechanism will return instantiations for topics and emotions as well as time intervals that provide the largest deflections in this measurement. Experiments are performed on a selection of Twitter data to demonstrates the usefulness of the approach.",
author = "Troels Andreasen and Henning Christiansen and Have, {Christian Theil}",
year = "2013",
language = "English",
isbn = "978-3-642-40768-0",
volume = "8132",
pages = "613--624",
booktitle = "Flexible Query Answering Systems",
publisher = "Springer",

}

Andreasen, T, Christiansen, H & Have, CT 2013, Querying Sentiment Development over Time. in Flexible Query Answering Systems: 10th International Conference, FQAS 2013, Granada, Spain, September 18-20, 2013. Proceedings. vol. 8132, Springer, Heidelberg, Lecture notes in artificial intelligence, vol. 8132, pp. 613-624.

Querying Sentiment Development over Time. / Andreasen, Troels; Christiansen, Henning; Have, Christian Theil.

Flexible Query Answering Systems: 10th International Conference, FQAS 2013, Granada, Spain, September 18-20, 2013. Proceedings. Vol. 8132 Heidelberg : Springer, 2013. p. 613-624.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Querying Sentiment Development over Time

AU - Andreasen, Troels

AU - Christiansen, Henning

AU - Have, Christian Theil

PY - 2013

Y1 - 2013

N2 - A new language is introduced for describing hypotheses about fluctuations of measurable properties in streams of timestamped data, and as prime example, we consider trends of emotions in the constantly flowing stream of Twitter messages. The language, called EmoEpisodes, has a precise semantics that measures how well a hypothesis characterizes a given time interval; the semantics is parameterized so it can be adjusted to different views of the data. EmoEpisodes is extended to a query language with variables standing for unknown topics and emotions, and the query-answering mechanism will return instantiations for topics and emotions as well as time intervals that provide the largest deflections in this measurement. Experiments are performed on a selection of Twitter data to demonstrates the usefulness of the approach.

AB - A new language is introduced for describing hypotheses about fluctuations of measurable properties in streams of timestamped data, and as prime example, we consider trends of emotions in the constantly flowing stream of Twitter messages. The language, called EmoEpisodes, has a precise semantics that measures how well a hypothesis characterizes a given time interval; the semantics is parameterized so it can be adjusted to different views of the data. EmoEpisodes is extended to a query language with variables standing for unknown topics and emotions, and the query-answering mechanism will return instantiations for topics and emotions as well as time intervals that provide the largest deflections in this measurement. Experiments are performed on a selection of Twitter data to demonstrates the usefulness of the approach.

M3 - Article in proceedings

SN - 978-3-642-40768-0

VL - 8132

SP - 613

EP - 624

BT - Flexible Query Answering Systems

PB - Springer

CY - Heidelberg

ER -

Andreasen T, Christiansen H, Have CT. Querying Sentiment Development over Time. In Flexible Query Answering Systems: 10th International Conference, FQAS 2013, Granada, Spain, September 18-20, 2013. Proceedings. Vol. 8132. Heidelberg: Springer. 2013. p. 613-624. (Lecture notes in artificial intelligence, Vol. 8132).