@article{de_nart_personalized_2014,
	title = {A {Personalized} {Concept}-driven {Recommender} {System} for {Scientific} {Libraries}},
	volume = {38},
	issn = {1877-0509},
	url = {http://www.sciencedirect.com/science/article/pii/S1877050914013751},
	doi = {10.1016/j.procs.2014.10.015},
	abstract = {Recommender Systems can greatly enhance the exploitation of large digital
libraries; however, in order to achieve good accuracy with collaborative
recommenders some domain assumptions must be met, such as having a large
number of users sharing similar interests over time. Such assumptions may
not hold in digital libraries, where users are structured in relatively
small groups of experts whose interests may change in unpredictable ways:
this is the case of scientific and technical documents archives. Moreover,
when recommending documents, users often expect insights on the
recommended content as well as a detailed explanation of why the system
has selected it, which cannot be provided by collaborative techniques. In
this paper we consider the domain of scientific publications repositories
and propose a content-based recommender based upon a graph representation
of concepts built up by linked keyphrases. This recommender is coupled
with a keyphrase extraction system able to generate meaningful metadata
for the documents, which are the basis for providing helpful and
explainable recommendations.},
	urldate = {2015-09-23},
	journal = {Procedia Comput. Sci.},
	author = {De Nart, D and Tasso, C},
	year = {2014},
	pages = {84--91},
}

{"_id":"hGWx5dcqjWknb6dSx","bibbaseid":"denart-tasso-apersonalizedconceptdrivenrecommendersystemforscientificlibraries-2014","authorIDs":[],"author_short":["De Nart, D","Tasso, C"],"bibdata":{"bibtype":"article","type":"article","title":"A Personalized Concept-driven Recommender System for Scientific Libraries","volume":"38","issn":"1877-0509","url":"http://www.sciencedirect.com/science/article/pii/S1877050914013751","doi":"10.1016/j.procs.2014.10.015","abstract":"Recommender Systems can greatly enhance the exploitation of large digital libraries; however, in order to achieve good accuracy with collaborative recommenders some domain assumptions must be met, such as having a large number of users sharing similar interests over time. Such assumptions may not hold in digital libraries, where users are structured in relatively small groups of experts whose interests may change in unpredictable ways: this is the case of scientific and technical documents archives. Moreover, when recommending documents, users often expect insights on the recommended content as well as a detailed explanation of why the system has selected it, which cannot be provided by collaborative techniques. In this paper we consider the domain of scientific publications repositories and propose a content-based recommender based upon a graph representation of concepts built up by linked keyphrases. This recommender is coupled with a keyphrase extraction system able to generate meaningful metadata for the documents, which are the basis for providing helpful and explainable recommendations.","urldate":"2015-09-23","journal":"Procedia Comput. Sci.","author":[{"propositions":[],"lastnames":["De","Nart"],"firstnames":["D"],"suffixes":[]},{"propositions":[],"lastnames":["Tasso"],"firstnames":["C"],"suffixes":[]}],"year":"2014","pages":"84–91","bibtex":"@article{de_nart_personalized_2014,\n\ttitle = {A {Personalized} {Concept}-driven {Recommender} {System} for {Scientific} {Libraries}},\n\tvolume = {38},\n\tissn = {1877-0509},\n\turl = {http://www.sciencedirect.com/science/article/pii/S1877050914013751},\n\tdoi = {10.1016/j.procs.2014.10.015},\n\tabstract = {Recommender Systems can greatly enhance the exploitation of large digital\nlibraries; however, in order to achieve good accuracy with collaborative\nrecommenders some domain assumptions must be met, such as having a large\nnumber of users sharing similar interests over time. Such assumptions may\nnot hold in digital libraries, where users are structured in relatively\nsmall groups of experts whose interests may change in unpredictable ways:\nthis is the case of scientific and technical documents archives. Moreover,\nwhen recommending documents, users often expect insights on the\nrecommended content as well as a detailed explanation of why the system\nhas selected it, which cannot be provided by collaborative techniques. In\nthis paper we consider the domain of scientific publications repositories\nand propose a content-based recommender based upon a graph representation\nof concepts built up by linked keyphrases. This recommender is coupled\nwith a keyphrase extraction system able to generate meaningful metadata\nfor the documents, which are the basis for providing helpful and\nexplainable recommendations.},\n\turldate = {2015-09-23},\n\tjournal = {Procedia Comput. Sci.},\n\tauthor = {De Nart, D and Tasso, C},\n\tyear = {2014},\n\tpages = {84--91},\n}\n\n","author_short":["De Nart, D","Tasso, C"],"key":"de_nart_personalized_2014","id":"de_nart_personalized_2014","bibbaseid":"denart-tasso-apersonalizedconceptdrivenrecommendersystemforscientificlibraries-2014","role":"author","urls":{"Paper":"http://www.sciencedirect.com/science/article/pii/S1877050914013751"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://api.zotero.org/users/6655/collections/TJPPJ92X/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","creationDate":"2020-03-27T02:34:35.335Z","downloads":0,"keywords":[],"search_terms":["personalized","concept","driven","recommender","system","scientific","libraries","de nart","tasso"],"title":"A Personalized Concept-driven Recommender System for Scientific Libraries","year":2014,"dataSources":["5Dp4QphkvpvNA33zi","jfoasiDDpStqkkoZB","SurqnJMScwdxRSFd5","CT2QdQoQtu2wab8TD","JGNRjejujgZaT5Woe","Rg7mRMhmZYnCLLEgE","2jPTcmjEXPKsta6A2","M95Ltr7FcMNgDrNnS","aQjY3RHAbbYYbJAHQ","BiuuFc45aHCgJqDLY"]}