| Item type |
SIG Technical Reports(1) |
| 公開日 |
2020-02-08 |
| タイトル |
|
|
タイトル |
Author-Oriented Book Recommendation Using Linked Open Data for Improving Serendipity |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Author-Oriented Book Recommendation Using Linked Open Data for Improving Serendipity |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
Graduate School of Library, Information and Media Studies, University of Tsukuba |
| 著者所属 |
|
|
|
Faculty of Library, Information and Media Science, University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
Graduate School of Library, Information and Media Studies, University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
Faculty of Library, Information and Media Science, University of Tsukuba |
| 著者名 |
Renlou, Weng
Masao, Takaku
|
| 著者名(英) |
Renlou, Weng
Masao, Takaku
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Recent years, recommender systems (RSs) are being used in many scenarios, such as online shopping stores, movie website and so on. However, many recommendation algorithms focus on accuracy based on a user profile, which may lead to reducing the user's satisfaction. This paper focuses on improving serendipity in RSs. In order to improving serendipity in book RS, two approaches are used in this paper: Linked Open Data (LOD) resource and author-oriented method. In addition, we implement our book RS and conducted a user experiment for evaluating the serendipity in book RS. We set two metrics for evaluating serendipity. As a result, the ratio of serendipitous books in top-10 list is 38.57% for author-oriented. Additionally, our method shows higher Novelty than baseline, even if Unexpectedness and Relevance are the same level with the baseline. Moreover, our method based recommendation tends to be more difficult for users to discover and much to users' surprise. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Recent years, recommender systems (RSs) are being used in many scenarios, such as online shopping stores, movie website and so on. However, many recommendation algorithms focus on accuracy based on a user profile, which may lead to reducing the user's satisfaction. This paper focuses on improving serendipity in RSs. In order to improving serendipity in book RS, two approaches are used in this paper: Linked Open Data (LOD) resource and author-oriented method. In addition, we implement our book RS and conducted a user experiment for evaluating the serendipity in book RS. We set two metrics for evaluating serendipity. As a result, the ratio of serendipitous books in top-10 list is 38.57% for author-oriented. Additionally, our method shows higher Novelty than baseline, even if Unexpectedness and Relevance are the same level with the baseline. Moreover, our method based recommendation tends to be more difficult for users to discover and much to users' surprise. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AN10114171 |
| 書誌情報 |
研究報告情報基礎とアクセス技術（IFAT）
巻 2020-IFAT-137,
号 1,
p. 1-6,
発行日 2020-02-08
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8884 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-IFAT20137001.pdf (1.4 MB)
