Individual Expert Selection and Ranking of Scientific Articles Using Document Length
Individual expert selection and ranking is a challenging research topic that has received a lot attention in recent years because of its importance related to referencing experts in particular domains and research fund allocation and management. In this work, scientific articles were used as the mos...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
ITB Journal Publisher
2019-04-01
|
| Series: | Journal of ICT Research and Applications |
| Subjects: | |
| Online Access: | http://journals.itb.ac.id/index.php/jictra/article/view/9181 |
| _version_ | 1818777872329867264 |
|---|---|
| author | Fadly Akbar Saputra Taufik Djatna Laksana Tri Handoko |
| author_facet | Fadly Akbar Saputra Taufik Djatna Laksana Tri Handoko |
| author_sort | Fadly Akbar Saputra |
| collection | DOAJ |
| description | Individual expert selection and ranking is a challenging research topic that has received a lot attention in recent years because of its importance related to referencing experts in particular domains and research fund allocation and management. In this work, scientific articles were used as the most common source for ranking expertise in particular domains. Previous studies only considered title and abstract content using language modeling. This study used the whole content of scientific documents obtained from Aminer citation data. The modified weighted language model (MWLM) is proposed that combines document length and number of citations as prior document probability to improve precision. Also, the author's dominance in a single document is computed using the Learning-to-Rank (L2R) method. The evaluation results using p@n, MAP, MRR, r-prec, and bpref showed a precision enhancement. MWLM improved the weighted language model (WLM) by p@n (4%), MAP (22.5%), and bpref (1.7%). MWLM also improved the precision of a model that used author dominance by MAP (4.3%), r-prec (8.2%), and bpref (2.1%). |
| first_indexed | 2024-12-18T11:35:44Z |
| format | Article |
| id | doaj.art-a1987acff316412fadd791131f7ec73c |
| institution | Directory Open Access Journal |
| issn | 2337-5787 2338-5499 |
| language | English |
| last_indexed | 2024-12-18T11:35:44Z |
| publishDate | 2019-04-01 |
| publisher | ITB Journal Publisher |
| record_format | Article |
| series | Journal of ICT Research and Applications |
| spelling | doaj.art-a1987acff316412fadd791131f7ec73c2022-12-21T21:09:31ZengITB Journal PublisherJournal of ICT Research and Applications2337-57872338-54992019-04-0113110.5614/itbj.ict.res.appl.2019.13.1.3Individual Expert Selection and Ranking of Scientific Articles Using Document LengthFadly Akbar Saputra0Taufik Djatna1Laksana Tri Handoko2Department of Computer Science, Faculty of Mathematics and Natural Science, Bogor Agricultural University, Kampus IPB Darmaga, Bogor 16680,Department of Agroindustrial Technology, Faculty of Agricultural Technology, Bogor Agricultural University, Kampus IPB Darmaga, Bogor 16680,Indonesian Institute of Science, Sasana Widya Sarwono (SWS) Jend. Gatot Subroto Street 10, South JakartaIndividual expert selection and ranking is a challenging research topic that has received a lot attention in recent years because of its importance related to referencing experts in particular domains and research fund allocation and management. In this work, scientific articles were used as the most common source for ranking expertise in particular domains. Previous studies only considered title and abstract content using language modeling. This study used the whole content of scientific documents obtained from Aminer citation data. The modified weighted language model (MWLM) is proposed that combines document length and number of citations as prior document probability to improve precision. Also, the author's dominance in a single document is computed using the Learning-to-Rank (L2R) method. The evaluation results using p@n, MAP, MRR, r-prec, and bpref showed a precision enhancement. MWLM improved the weighted language model (WLM) by p@n (4%), MAP (22.5%), and bpref (1.7%). MWLM also improved the precision of a model that used author dominance by MAP (4.3%), r-prec (8.2%), and bpref (2.1%).http://journals.itb.ac.id/index.php/jictra/article/view/9181document lengthindividual expertlanguage modelscientific articleselection and ranking |
| spellingShingle | Fadly Akbar Saputra Taufik Djatna Laksana Tri Handoko Individual Expert Selection and Ranking of Scientific Articles Using Document Length Journal of ICT Research and Applications document length individual expert language model scientific article selection and ranking |
| title | Individual Expert Selection and Ranking of Scientific Articles Using Document Length |
| title_full | Individual Expert Selection and Ranking of Scientific Articles Using Document Length |
| title_fullStr | Individual Expert Selection and Ranking of Scientific Articles Using Document Length |
| title_full_unstemmed | Individual Expert Selection and Ranking of Scientific Articles Using Document Length |
| title_short | Individual Expert Selection and Ranking of Scientific Articles Using Document Length |
| title_sort | individual expert selection and ranking of scientific articles using document length |
| topic | document length individual expert language model scientific article selection and ranking |
| url | http://journals.itb.ac.id/index.php/jictra/article/view/9181 |
| work_keys_str_mv | AT fadlyakbarsaputra individualexpertselectionandrankingofscientificarticlesusingdocumentlength AT taufikdjatna individualexpertselectionandrankingofscientificarticlesusingdocumentlength AT laksanatrihandoko individualexpertselectionandrankingofscientificarticlesusingdocumentlength |