Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications.
Finding relevant publications is important for scientists who have to cope with exponentially increasing numbers of scholarly material. Algorithms can help with this task as they help for music, movie, and product recommendations. However, we know little about the performance of these algorithms wit...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2016-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC4934767?pdf=render |
| _version_ | 1828371389365616640 |
|---|---|
| author | Titipat Achakulvisut Daniel E Acuna Tulakan Ruangrong Konrad Kording |
| author_facet | Titipat Achakulvisut Daniel E Acuna Tulakan Ruangrong Konrad Kording |
| author_sort | Titipat Achakulvisut |
| collection | DOAJ |
| description | Finding relevant publications is important for scientists who have to cope with exponentially increasing numbers of scholarly material. Algorithms can help with this task as they help for music, movie, and product recommendations. However, we know little about the performance of these algorithms with scholarly material. Here, we develop an algorithm, and an accompanying Python library, that implements a recommendation system based on the content of articles. Design principles are to adapt to new content, provide near-real time suggestions, and be open source. We tested the library on 15K posters from the Society of Neuroscience Conference 2015. Human curated topics are used to cross validate parameters in the algorithm and produce a similarity metric that maximally correlates with human judgments. We show that our algorithm significantly outperformed suggestions based on keywords. The work presented here promises to make the exploration of scholarly material faster and more accurate. |
| first_indexed | 2024-04-14T06:49:06Z |
| format | Article |
| id | doaj.art-14274f2605754278ab5a24d42c4ffa5c |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-14T06:49:06Z |
| publishDate | 2016-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-14274f2605754278ab5a24d42c4ffa5c2022-12-22T02:07:05ZengPublic Library of Science (PLoS)PLoS ONE1932-62032016-01-01117e015842310.1371/journal.pone.0158423Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications.Titipat AchakulvisutDaniel E AcunaTulakan RuangrongKonrad KordingFinding relevant publications is important for scientists who have to cope with exponentially increasing numbers of scholarly material. Algorithms can help with this task as they help for music, movie, and product recommendations. However, we know little about the performance of these algorithms with scholarly material. Here, we develop an algorithm, and an accompanying Python library, that implements a recommendation system based on the content of articles. Design principles are to adapt to new content, provide near-real time suggestions, and be open source. We tested the library on 15K posters from the Society of Neuroscience Conference 2015. Human curated topics are used to cross validate parameters in the algorithm and produce a similarity metric that maximally correlates with human judgments. We show that our algorithm significantly outperformed suggestions based on keywords. The work presented here promises to make the exploration of scholarly material faster and more accurate.http://europepmc.org/articles/PMC4934767?pdf=render |
| spellingShingle | Titipat Achakulvisut Daniel E Acuna Tulakan Ruangrong Konrad Kording Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications. PLoS ONE |
| title | Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications. |
| title_full | Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications. |
| title_fullStr | Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications. |
| title_full_unstemmed | Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications. |
| title_short | Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications. |
| title_sort | science concierge a fast content based recommendation system for scientific publications |
| url | http://europepmc.org/articles/PMC4934767?pdf=render |
| work_keys_str_mv | AT titipatachakulvisut scienceconciergeafastcontentbasedrecommendationsystemforscientificpublications AT danieleacuna scienceconciergeafastcontentbasedrecommendationsystemforscientificpublications AT tulakanruangrong scienceconciergeafastcontentbasedrecommendationsystemforscientificpublications AT konradkording scienceconciergeafastcontentbasedrecommendationsystemforscientificpublications |