Lentis/Software Journalism: When Programs Write the News: Difference between revisions
| [checked revision] | [unreviewed revision] |
m + cat |
No edit summary |
||
| Line 2: | Line 2: | ||
==Background== |
==Background== |
||
Software Journalism, sometimes called Robot Journalism, is the use of computer programs to automatically generate textual narratives from structured data. |
Software Journalism, sometimes called Robot Journalism, is the use of computer programs to automatically generate textual narratives from structured data. |
||
===Algorithms=== |
===Algorithms=== |
||
Software Journalism |
Software Journalism applications use algorithms that quickly create lots of stories for a given topic. These algorithms are best at writing stories for repetitive topics that have clean, accurate and structured data available. Organizations that want to cut costs and produce more news use Software Journalism algorithms. |
||
<ref>Graeffe, A. (2016, Janruary 7). Guide to Automated Journalism. http://towcenter.org/research/guide-to-automated-journalism/</ref>. |
|||
Software Journalism algorithms generate news faster and at a larger scale than human journalists. The same data can be used to produce stories in many languages and from different angles. |
|||
Software Journalism algorithms have limitations. They can be subject to bias and error due to an algorithm's assumptions about and reliance on data. Algorithms are limited in making analytical insights since they can't ask questions or explain phenomena<ref>Graeffe, A. (2016, January 7). Guide to Automated Journalism. http://towcenter.org/research/guide-to-automated-journalism/</ref>. |
|||
====NLG vs NLP==== |
====NLG vs NLP==== |
||
Software Journalism programs use Natural Language Generation (NLG) to create content. NLG is the counterpart of Natural Language Processing (NLP). NLP converts text into structured data, whereas NLG generates contextual narratives from data. Both NLP and NLG are fields of Artificial Intelligence <ref>Wright, A. doi:10.1145/2820421</ref>. |
|||
===Why Use Software Journalism?=== |
|||
Software Journalism allows content producers to quickly identify facts that are important to the narrative through seamless data source integration. A story can be generated automatically with any size dataset. The narrative produced is almost undistinguishable from written by a human journalist and can be personalized per individual. |
|||
Employee productivity increases due to Software Journalism. Reporting and time consuming data analysis is covered by the software. This allows employees to focus on personal growth and higher level content generation<ref>Narrative Science. (2016). Quill. https://www.narrativescience.com/quill</ref>. |
|||
===NLG Companies=== |
===NLG Companies=== |
||
{| class="wikitable" |
{| class="wikitable" |
||
Revision as of 22:21, 5 December 2016
Software Journalism is the use of computer programs to write news. These programs take in data to produce human-readable stories. This chapter explores the social interaction of Software Journalism, news producers and news consumers.
Background
Software Journalism, sometimes called Robot Journalism, is the use of computer programs to automatically generate textual narratives from structured data.
Algorithms
Software Journalism applications use algorithms that quickly create lots of stories for a given topic. These algorithms are best at writing stories for repetitive topics that have clean, accurate and structured data available. Organizations that want to cut costs and produce more news use Software Journalism algorithms.
Software Journalism algorithms generate news faster and at a larger scale than human journalists. The same data can be used to produce stories in many languages and from different angles.
Software Journalism algorithms have limitations. They can be subject to bias and error due to an algorithm's assumptions about and reliance on data. Algorithms are limited in making analytical insights since they can't ask questions or explain phenomena[1].
NLG vs NLP
Software Journalism programs use Natural Language Generation (NLG) to create content. NLG is the counterpart of Natural Language Processing (NLP). NLP converts text into structured data, whereas NLG generates contextual narratives from data. Both NLP and NLG are fields of Artificial Intelligence [2].
Why Use Software Journalism?
Software Journalism allows content producers to quickly identify facts that are important to the narrative through seamless data source integration. A story can be generated automatically with any size dataset. The narrative produced is almost undistinguishable from written by a human journalist and can be personalized per individual.
Employee productivity increases due to Software Journalism. Reporting and time consuming data analysis is covered by the software. This allows employees to focus on personal growth and higher level content generation[3].
NLG Companies
| Company | Product |
|---|---|
| Narrative Science | Quill |
| Automated Insights | Wordsmith |
| Arria | Arria NLG |
References
- ↑ Graeffe, A. (2016, January 7). Guide to Automated Journalism. http://towcenter.org/research/guide-to-automated-journalism/
- ↑ Wright, A. doi:10.1145/2820421
- ↑ Narrative Science. (2016). Quill. https://www.narrativescience.com/quill