Language for Granted - Automatic Evalutation of the Language Used in Grant Applications
(2007)General Linguistics
- Abstract
- Abstract
This thesis examines whether it is possible to ascertain a measurable difference between granted and refused grant applications with automatic methods. A corpus of project descriptions from the Swedish Science Council was examined with different classification techniques and using different linguistic features. A Naive Bayes classifier is shown to be a good predictor for this type of problem and the number of prepositional phrases in a document is shown to be a good attribute for classification. The results show that there does exist a statistically measurable linguistic difference between granted and refused applications.
Sammanfattning
Denna uppsats undersöker om det går att, med automatiska metoder, mäta en skillnad mellan... (More) - Abstract
This thesis examines whether it is possible to ascertain a measurable difference between granted and refused grant applications with automatic methods. A corpus of project descriptions from the Swedish Science Council was examined with different classification techniques and using different linguistic features. A Naive Bayes classifier is shown to be a good predictor for this type of problem and the number of prepositional phrases in a document is shown to be a good attribute for classification. The results show that there does exist a statistically measurable linguistic difference between granted and refused applications.
Sammanfattning
Denna uppsats undersöker om det går att, med automatiska metoder, mäta en skillnad mellan godkända och avslagna bidragsansökningar. En korpus med projektbeskrivningar från Vetenskapsrådet undersöktes med olika klassifikationstekniker för olika lingvistiska särdrag. Det visar sig att en "Naive Bayes"-klassificerare fungerar bra för denna slags problem och också att antalet prepositionsfraser i ett dokument är en bra utgångspunkt för klassificering. Resultaten visar slutligen att det finns en statistiskt mätbar språklig skillnad mellan godkända och avslagna ansökningar. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/1325493
- author
- Sällström Randsalu, Peeter
- supervisor
- organization
- year
- 2007
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- Language Technology, Text Categorization, Grant Applications, Linguistics, Allmän språkvetenskap/Lingvistik
- language
- English
- id
- 1325493
- date added to LUP
- 2007-11-24 00:00:00
- date last changed
- 2008-07-08 00:00:00
@misc{1325493,
abstract = {{Abstract
This thesis examines whether it is possible to ascertain a measurable difference between granted and refused grant applications with automatic methods. A corpus of project descriptions from the Swedish Science Council was examined with different classification techniques and using different linguistic features. A Naive Bayes classifier is shown to be a good predictor for this type of problem and the number of prepositional phrases in a document is shown to be a good attribute for classification. The results show that there does exist a statistically measurable linguistic difference between granted and refused applications.
Sammanfattning
Denna uppsats undersöker om det går att, med automatiska metoder, mäta en skillnad mellan godkända och avslagna bidragsansökningar. En korpus med projektbeskrivningar från Vetenskapsrådet undersöktes med olika klassifikationstekniker för olika lingvistiska särdrag. Det visar sig att en "Naive Bayes"-klassificerare fungerar bra för denna slags problem och också att antalet prepositionsfraser i ett dokument är en bra utgångspunkt för klassificering. Resultaten visar slutligen att det finns en statistiskt mätbar språklig skillnad mellan godkända och avslagna ansökningar.}},
author = {{Sällström Randsalu, Peeter}},
language = {{eng}},
note = {{Student Paper}},
title = {{Language for Granted - Automatic Evalutation of the Language Used in Grant Applications}},
year = {{2007}},
}