Discourse parsing of sociology dissertation abstracts using decision tree induction
In this study, we investigated the use of decision tree induction to parse the macro-level discourse structure of sociology dissertation abstracts. We treated discourse parsing as a sentence categorization task. The attributes used in constructing the dec...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/93813 http://hdl.handle.net/10220/7296 |
| _version_ | 1811676497696522240 |
|---|---|
| author | Ou, Shiyan Heng, Hui Ying Goh, Dion Hoe-Lian Khoo, Christopher S. G. |
| author2 | Wee Kim Wee School of Communication and Information |
| author_facet | Wee Kim Wee School of Communication and Information Ou, Shiyan Heng, Hui Ying Goh, Dion Hoe-Lian Khoo, Christopher S. G. |
| author_sort | Ou, Shiyan |
| collection | NTU |
| description | In this study, we investigated the use of decision tree induction to
parse the macro-level discourse structure of sociology dissertation abstracts.
We treated discourse parsing as a sentence categorization task. The attributes
used in constructing the decision tree models were stemmed words that
occurred in at least 35 sentences (out of 3694 sentences in 300 sample
abstracts). Sentence location information was also used. The model obtained
an accuracy rate of 71.3% when applied to a test sample of 100 abstracts.
Another model that made use of information regarding the presence of 31
indicator words in neighboring sentences was also developed. Although this
model did not obtain better results, a comparison of the two models suggests
that an improvement in the classification of sentences in problem statement
and research method section is possible by combining the models. |
| first_indexed | 2024-10-01T02:22:25Z |
| format | Conference Paper |
| id | ntu-10356/93813 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:22:25Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/938132019-12-06T18:45:58Z Discourse parsing of sociology dissertation abstracts using decision tree induction Ou, Shiyan Heng, Hui Ying Goh, Dion Hoe-Lian Khoo, Christopher S. G. Wee Kim Wee School of Communication and Information 14th ASIS SIG/CR Classification Research Workshop DRNTU::Library and information science In this study, we investigated the use of decision tree induction to parse the macro-level discourse structure of sociology dissertation abstracts. We treated discourse parsing as a sentence categorization task. The attributes used in constructing the decision tree models were stemmed words that occurred in at least 35 sentences (out of 3694 sentences in 300 sample abstracts). Sentence location information was also used. The model obtained an accuracy rate of 71.3% when applied to a test sample of 100 abstracts. Another model that made use of information regarding the presence of 31 indicator words in neighboring sentences was also developed. Although this model did not obtain better results, a comparison of the two models suggests that an improvement in the classification of sentences in problem statement and research method section is possible by combining the models. Published version 2011-10-18T01:23:50Z 2019-12-06T18:45:58Z 2011-10-18T01:23:50Z 2019-12-06T18:45:58Z 2003 2003 Conference Paper Ou, S., Khoo, C. S. G., Heng, H. Y., & Goh, D. H. L. (2003). Discourse Parsing of Sociology Dissertation Abstracts Using Decision Tree Induction. In Proceedings of the 14th Annual ASIST SIG CR Workshop, Long Beach, California, USA. https://hdl.handle.net/10356/93813 http://hdl.handle.net/10220/7296 en © 2009 The Author(s) (ASIS SIG/CR Classification Research Workshop). This paper was published in Proceedings of the 14th ASIS SIG/CR Classification Research Workshop and is made available as an electronic reprint (preprint) with permission of The Author(s) (ASIS SIG/CR Classification Research Workshop). The published version is available at: [http://journals.lib.washington.edu/index.php/acro/article/view/14114]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law. 9 p. application/pdf |
| spellingShingle | DRNTU::Library and information science Ou, Shiyan Heng, Hui Ying Goh, Dion Hoe-Lian Khoo, Christopher S. G. Discourse parsing of sociology dissertation abstracts using decision tree induction |
| title | Discourse parsing of sociology dissertation abstracts using decision tree induction |
| title_full | Discourse parsing of sociology dissertation abstracts using decision tree induction |
| title_fullStr | Discourse parsing of sociology dissertation abstracts using decision tree induction |
| title_full_unstemmed | Discourse parsing of sociology dissertation abstracts using decision tree induction |
| title_short | Discourse parsing of sociology dissertation abstracts using decision tree induction |
| title_sort | discourse parsing of sociology dissertation abstracts using decision tree induction |
| topic | DRNTU::Library and information science |
| url | https://hdl.handle.net/10356/93813 http://hdl.handle.net/10220/7296 |
| work_keys_str_mv | AT oushiyan discourseparsingofsociologydissertationabstractsusingdecisiontreeinduction AT henghuiying discourseparsingofsociologydissertationabstractsusingdecisiontreeinduction AT gohdionhoelian discourseparsingofsociologydissertationabstractsusingdecisiontreeinduction AT khoochristophersg discourseparsingofsociologydissertationabstractsusingdecisiontreeinduction |