Difference between revisions of "Citolytics: a Link-Based Recommender System for Wikipedia"
(Adding new article - Citolytics: a Link-Based Recommender System for Wikipedia) |
(+ wikilinks) |
||
| Line 1: | Line 1: | ||
| − | '''Citolytics: a Link-Based Recommender System for Wikipedia''' - scientific work related to Wikipedia quality published in 2017, written by Malte Schwarzer, Corinna Breitinger, Moritz Schubotz, Norman Meuschke and Bela Gipp. | + | '''Citolytics: a Link-Based Recommender System for Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2017, written by [[Malte Schwarzer]], [[Corinna Breitinger]], [[Moritz Schubotz]], [[Norman Meuschke]] and [[Bela Gipp]]. |
== Overview == | == Overview == | ||
| − | Authors present Citolytics - a novel link-based recommendation system for Wikipedia articles. In a preliminary study, Citolytics achieved promising results compared to the widely used text-based approach of Apache Lucene's MoreLikeThis (MLT). In this demo paper, authors describe how authors plan to integrate Citolytics into the Wikipedia infrastructure by using Elasticsearch and Apache Flink to serve recommendations for Wikipedia articles. Additionally, authors propose a large-scale online evaluation design using the Wikipedia Android app. Working with Wikipedia data has several unique advantages. First, the availability of a very large user sample contributes to statistically significant results. Second, the openness of Wikipedia's architecture allows making source code and evaluation data public, thus benefiting other researchers. If link-based recommendations show promise in online evaluation, a deployment of the presented system within Wikipedia would have a far-reaching impact on Wikipedia's more than 30 million users. | + | Authors present Citolytics - a novel link-based recommendation system for [[Wikipedia]] articles. In a preliminary study, Citolytics achieved promising results compared to the widely used text-based approach of Apache Lucene's MoreLikeThis (MLT). In this demo paper, authors describe how authors plan to integrate Citolytics into the Wikipedia infrastructure by using Elasticsearch and Apache Flink to serve recommendations for Wikipedia articles. Additionally, authors propose a large-scale online evaluation design using the Wikipedia Android app. Working with Wikipedia data has several unique advantages. First, the availability of a very large user sample contributes to statistically significant results. Second, the openness of Wikipedia's architecture allows making source code and evaluation data public, thus benefiting other researchers. If link-based recommendations show promise in online evaluation, a deployment of the presented system within Wikipedia would have a far-reaching impact on Wikipedia's more than 30 million users. |
Revision as of 11:36, 8 September 2019
Citolytics: a Link-Based Recommender System for Wikipedia - scientific work related to Wikipedia quality published in 2017, written by Malte Schwarzer, Corinna Breitinger, Moritz Schubotz, Norman Meuschke and Bela Gipp.
Overview
Authors present Citolytics - a novel link-based recommendation system for Wikipedia articles. In a preliminary study, Citolytics achieved promising results compared to the widely used text-based approach of Apache Lucene's MoreLikeThis (MLT). In this demo paper, authors describe how authors plan to integrate Citolytics into the Wikipedia infrastructure by using Elasticsearch and Apache Flink to serve recommendations for Wikipedia articles. Additionally, authors propose a large-scale online evaluation design using the Wikipedia Android app. Working with Wikipedia data has several unique advantages. First, the availability of a very large user sample contributes to statistically significant results. Second, the openness of Wikipedia's architecture allows making source code and evaluation data public, thus benefiting other researchers. If link-based recommendations show promise in online evaluation, a deployment of the presented system within Wikipedia would have a far-reaching impact on Wikipedia's more than 30 million users.
