Name
Abstract | ||
|---|---|---|
Position describes the tendency of users to interact with items on top of a list with higher probability than with items at a lower position in the list, regardless of the itemsu0027 actual relevance. In the domain of recommender systems, particularly recommender systems in digital libraries, position bias has received little attention. We conduct a study in a real-world recommender system that delivered ten million related-article recommendations to the users of the digital library Sowiport, and the reference manager JabRef. Recommendations were randomly chosen to be shuffled or non-shuffled, and we compared click-through rate (CTR) for each rank of the recommendations. According to our analysis, the CTR for the highest rank in the case of Sowiport is 53% higher than expected in a hypothetical non-biased situation (0.189% vs. 0.123%). Similarly, in the case of Jabref the highest rank received a CTR of 1.276%, which is 87% higher than expected (0.683%). A chi-squared test confirms the strong relationship between the rank of the recommendation shown to the user and whether the user decided to click it (p u003c 0.01 for both Jabref and Sowiport). Our study confirms the findings from other domains, that recommendations in the top positions are more often clicked, regardless of their actual relevance. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Digital Libraries | Recommender system,Data mining,Information retrieval,Computer science,Digital library |
DocType | Volume | Citations |
Journal | abs/1802.06565 | 1 |
PageRank | References | Authors |
0.41 | 17 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Andrew Collins | 1 | 1 | 5.82 |
| Dominika Tkaczyk | 2 | 65 | 7.23 |
| Akiko N. Aizawa | 3 | 678 | 120.63 |
| Jöran Beel | 4 | 65 | 9.60 |