@inproceedings{
 title = {Random Walks on Human Knowledge: Incorporating Human Knowledge into Data-Driven Recommenders},
 type = {inproceedings},
 year = {2018},
 keywords = {Knowledge Representation,Knowledge representation,Random Walks,Random walks,Recommender Systems,Recommender systems},
 pages = {63-72},
 volume = {3},
 websites = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006893900630072},
 publisher = {SCITEPRESS - Science and Technology Publications},
 institution = {INSTICC},
 id = {8280970d-e765-3191-ac2f-32921801cb02},
 created = {2022-08-22T10:15:22.095Z},
 file_attached = {true},
 profile_id = {e4ed3238-8302-3280-bd05-0b185874fb43},
 last_modified = {2022-08-22T12:28:05.686Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {kmis18},
 source_type = {conference},
 folder_uuids = {b35e5b0c-63da-4577-ad8a-01a619ce7c0b},
 private_publication = {false},
 abstract = {We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.},
 bibtype = {inproceedings},
 author = {Witschel, H.F. Hans Friedrich and Martin, Andreas},
 doi = {10.5220/0006893900630072},
 booktitle = {Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management}
}

{"_id":"5LWCZ7cTbNK2igKLM","bibbaseid":"witschel-martin-randomwalksonhumanknowledgeincorporatinghumanknowledgeintodatadrivenrecommenders-2018","downloads":1,"creationDate":"2018-09-27T11:50:54.159Z","title":"Random Walks on Human Knowledge: Incorporating Human Knowledge into Data-Driven Recommenders","author_short":["Witschel, H., H., F.","Martin, A."],"year":2018,"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/e4ed3238-8302-3280-bd05-0b185874fb43","bibdata":{"title":"Random Walks on Human Knowledge: Incorporating Human Knowledge into Data-Driven Recommenders","type":"inproceedings","year":"2018","keywords":"Knowledge Representation,Knowledge representation,Random Walks,Random walks,Recommender Systems,Recommender systems","pages":"63-72","volume":"3","websites":"http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006893900630072","publisher":"SCITEPRESS - Science and Technology Publications","institution":"INSTICC","id":"8280970d-e765-3191-ac2f-32921801cb02","created":"2022-08-22T10:15:22.095Z","file_attached":"true","profile_id":"e4ed3238-8302-3280-bd05-0b185874fb43","last_modified":"2022-08-22T12:28:05.686Z","read":"true","starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"kmis18","source_type":"conference","folder_uuids":"b35e5b0c-63da-4577-ad8a-01a619ce7c0b","private_publication":false,"abstract":"We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.","bibtype":"inproceedings","author":"Witschel, H.F. Hans Friedrich and Martin, Andreas","doi":"10.5220/0006893900630072","booktitle":"Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","bibtex":"@inproceedings{\n title = {Random Walks on Human Knowledge: Incorporating Human Knowledge into Data-Driven Recommenders},\n type = {inproceedings},\n year = {2018},\n keywords = {Knowledge Representation,Knowledge representation,Random Walks,Random walks,Recommender Systems,Recommender systems},\n pages = {63-72},\n volume = {3},\n websites = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006893900630072},\n publisher = {SCITEPRESS - Science and Technology Publications},\n institution = {INSTICC},\n id = {8280970d-e765-3191-ac2f-32921801cb02},\n created = {2022-08-22T10:15:22.095Z},\n file_attached = {true},\n profile_id = {e4ed3238-8302-3280-bd05-0b185874fb43},\n last_modified = {2022-08-22T12:28:05.686Z},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {kmis18},\n source_type = {conference},\n folder_uuids = {b35e5b0c-63da-4577-ad8a-01a619ce7c0b},\n private_publication = {false},\n abstract = {We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.},\n bibtype = {inproceedings},\n author = {Witschel, H.F. Hans Friedrich and Martin, Andreas},\n doi = {10.5220/0006893900630072},\n booktitle = {Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management}\n}","author_short":["Witschel, H., H., F.","Martin, A."],"urls":{"Website":"http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006893900630072"},"biburl":"https://bibbase.org/service/mendeley/e4ed3238-8302-3280-bd05-0b185874fb43","bibbaseid":"witschel-martin-randomwalksonhumanknowledgeincorporatinghumanknowledgeintodatadrivenrecommenders-2018","role":"author","keyword":["Knowledge Representation","Knowledge representation","Random Walks","Random walks","Recommender Systems","Recommender systems"],"metadata":{"authorlinks":{"martin, a":"https://bibbase.org/service/mendeley/e4ed3238-8302-3280-bd05-0b185874fb43"}},"downloads":1},"search_terms":["random","walks","human","knowledge","incorporating","human","knowledge","data","driven","recommenders","witschel","martin"],"keywords":["knowledge representation","knowledge representation","random walks","random walks","recommender systems","recommender systems"],"authorIDs":["8YQnBunpATPezhhEo"],"dataSources":["sjAoEKginzum6i3Ln","ya2CyA73rpZseyrZ8","jurZeGzSpYdkQ8rm4","cEgnxBqYRFNdjfnYF","za7JCis3wBjciTGFW","2252seNhipfTmjEBQ"]}