StatsMonkey

A data-driven sports narrative writer

Nicholas D. Allen, John R. Templon, Patrick Summerhays McNally, Larry Birnbaum, Kristian Hammond

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

There are certain types of stories that are often told in very structured ways; sports stories or financial reports are two examples. Readers care about these narratives because they are passionately interested in the topic and want to read about the specific details of the event. In other words, they care about the data and want to read a story that presents that data to them. However, in order to be compelling these narratives cannot merely repeat the data, rather they must tell a story from the data. In this paper, we will present a model for data-driven story-telling and discuss StatsMonkey, a system that automatically writes baseball stories from raw baseball game numerical data available online. We will show that a machine can generate interesting, readable stories and that it can make editorial decisions about what aspects of a situation to highlight. Further we will show that a machine can determine in what manner those aspects should be shared.

Original languageEnglish (US)
Title of host publicationComputational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report
Pages2-3
Number of pages2
VolumeFS-10-04
StatePublished - Dec 1 2010
Event2010 AAAI Fall Symposium - Arlington, VA, United States
Duration: Nov 11 2010Nov 13 2010

Other

Other2010 AAAI Fall Symposium
CountryUnited States
CityArlington, VA
Period11/11/1011/13/10

Fingerprint

Sports

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Allen, N. D., Templon, J. R., McNally, P. S., Birnbaum, L., & Hammond, K. (2010). StatsMonkey: A data-driven sports narrative writer. In Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report (Vol. FS-10-04, pp. 2-3)
Allen, Nicholas D. ; Templon, John R. ; McNally, Patrick Summerhays ; Birnbaum, Larry ; Hammond, Kristian. / StatsMonkey : A data-driven sports narrative writer. Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-10-04 2010. pp. 2-3
@inproceedings{8ea7ea09d1b54238925369a049cd98a7,
title = "StatsMonkey: A data-driven sports narrative writer",
abstract = "There are certain types of stories that are often told in very structured ways; sports stories or financial reports are two examples. Readers care about these narratives because they are passionately interested in the topic and want to read about the specific details of the event. In other words, they care about the data and want to read a story that presents that data to them. However, in order to be compelling these narratives cannot merely repeat the data, rather they must tell a story from the data. In this paper, we will present a model for data-driven story-telling and discuss StatsMonkey, a system that automatically writes baseball stories from raw baseball game numerical data available online. We will show that a machine can generate interesting, readable stories and that it can make editorial decisions about what aspects of a situation to highlight. Further we will show that a machine can determine in what manner those aspects should be shared.",
author = "Allen, {Nicholas D.} and Templon, {John R.} and McNally, {Patrick Summerhays} and Larry Birnbaum and Kristian Hammond",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781577354864",
volume = "FS-10-04",
pages = "2--3",
booktitle = "Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report",

}

Allen, ND, Templon, JR, McNally, PS, Birnbaum, L & Hammond, K 2010, StatsMonkey: A data-driven sports narrative writer. in Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report. vol. FS-10-04, pp. 2-3, 2010 AAAI Fall Symposium, Arlington, VA, United States, 11/11/10.

StatsMonkey : A data-driven sports narrative writer. / Allen, Nicholas D.; Templon, John R.; McNally, Patrick Summerhays; Birnbaum, Larry; Hammond, Kristian.

Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-10-04 2010. p. 2-3.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - StatsMonkey

T2 - A data-driven sports narrative writer

AU - Allen, Nicholas D.

AU - Templon, John R.

AU - McNally, Patrick Summerhays

AU - Birnbaum, Larry

AU - Hammond, Kristian

PY - 2010/12/1

Y1 - 2010/12/1

N2 - There are certain types of stories that are often told in very structured ways; sports stories or financial reports are two examples. Readers care about these narratives because they are passionately interested in the topic and want to read about the specific details of the event. In other words, they care about the data and want to read a story that presents that data to them. However, in order to be compelling these narratives cannot merely repeat the data, rather they must tell a story from the data. In this paper, we will present a model for data-driven story-telling and discuss StatsMonkey, a system that automatically writes baseball stories from raw baseball game numerical data available online. We will show that a machine can generate interesting, readable stories and that it can make editorial decisions about what aspects of a situation to highlight. Further we will show that a machine can determine in what manner those aspects should be shared.

AB - There are certain types of stories that are often told in very structured ways; sports stories or financial reports are two examples. Readers care about these narratives because they are passionately interested in the topic and want to read about the specific details of the event. In other words, they care about the data and want to read a story that presents that data to them. However, in order to be compelling these narratives cannot merely repeat the data, rather they must tell a story from the data. In this paper, we will present a model for data-driven story-telling and discuss StatsMonkey, a system that automatically writes baseball stories from raw baseball game numerical data available online. We will show that a machine can generate interesting, readable stories and that it can make editorial decisions about what aspects of a situation to highlight. Further we will show that a machine can determine in what manner those aspects should be shared.

UR - http://www.scopus.com/inward/record.url?scp=79960117278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960117278&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354864

VL - FS-10-04

SP - 2

EP - 3

BT - Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report

ER -

Allen ND, Templon JR, McNally PS, Birnbaum L, Hammond K. StatsMonkey: A data-driven sports narrative writer. In Computational Models of Narrative - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-10-04. 2010. p. 2-3