Conference paper Open Access

Profiling vs. Time vs. Content: What Does Matter for Top-k Publication Recommendation Based on Twitter Profiles?

Nishioka, Chifumi; Scherp, Ansgar


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="a">2017-06-19</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">recommender system</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">social media</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">user profiling</subfield>
  </datafield>
  <controlfield tag="005">20190410034616.0</controlfield>
  <controlfield tag="001">61391</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">June 19-23 2016</subfield>
    <subfield code="g">JCDL</subfield>
    <subfield code="a">16th ACM/IEEE-CS on Joint Conference on Digital Libraries</subfield>
    <subfield code="c">Newark, NJ, USA</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Kiel University and Leibniz Information Centre for Economics (ZBW)</subfield>
    <subfield code="a">Scherp, Ansgar</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1002985</subfield>
    <subfield code="z">md5:cea973833726c3688afc0ad28c896977</subfield>
    <subfield code="u">https://zenodo.org/record/61391/files/2016_jcdl_nishioka_profiling-vs-time-vs-content-what-does-matter-for-top-k-publication-recommendation-based-on-twitter-profiles.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">http://www.jcdl2016.org/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2016-06-19</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-ecfunded</subfield>
    <subfield code="p">user-moving-h2020</subfield>
    <subfield code="o">oai:zenodo.org:61391</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Kiel University and Leibniz Information Centre for Economics (ZBW)</subfield>
    <subfield code="a">Nishioka, Chifumi</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Profiling vs. Time vs. Content: What Does Matter for Top-k Publication Recommendation Based on Twitter Profiles?</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ecfunded</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-moving-h2020</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">693092</subfield>
    <subfield code="a">Training towards a society of data-savvy information professionals to enable open leadership innovation</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;So far it is unclear how different factors of a scientific publication recommender system based on users' tweets have an influence on the recommendation performance. We examine three different factors, namely profiling method, temporal decay, and richness of content. Regarding profiling, we compare CF-IDF that replaces terms in TF-IDF by semantic concepts, HCF-IDF as novel hierarchical variant of CF-IDF, and topic modeling. As temporal decay functions, we apply sliding window and exponential decay. In terms of the richness of content, we compare recommendations using both full-texts and titles of publications and using only titles. Overall, the three factors make twelve recommendation strategies. We have conducted an online experiment with 123 participants and compared the strategies in a within-group design. The best recommendations are achieved by the strategy combining CF-IDF, sliding window, and with full-texts. However, the strategies using the novel HCF-IDF profiling method achieve similar results with just using the titles of the publications. Therefore, HCF-IDF can make recommendations when only short and sparse data is available.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1145/2910896.2910898</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
34
15
views
downloads
Views 34
Downloads 15
Data volume 15.0 MB
Unique views 33
Unique downloads 15

Share

Cite as