Leveraging Collective Intelligence in Recommender System. Chang, S. Ph.D. Thesis, University of Minnesota, Minneapolis, MN, USA, August, 2016. ![Leveraging Collective Intelligence in Recommender System [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Recommender systems, since their introduction 20 years ago, have been widely deployed in web services to alleviate user information overload. Driven by business objectives of their applications, the focus of recommender systems has shifted from accurately modeling and predicting user preferences to offering good personalized user experience. The later is difficult because there are many factors, e.g., tenure of a user, context of recommendation and transparency of recommender system, that affect users' perception of recommendations. Many of these factors are subjective and not easily quantifiable, posing challenges to recommender algorithms. When pure algorithmic solutions are at their limits in providing good user experience in recommender systems, we turn to the collective intelligence of human and computer. Computer and human are complementary to each other: computers are fast at computation and data processing and have accurate memory; humans are capable of complex reasoning, being creative and relating to other humans. In fact, such close collaborations between human and computer have precedent: after chess master Garry Kasparov lost to IBM computer ``Deep Blue'', he invited a new form of chess — advanced chess, in which human player and a computer program teams up against such pairs. In this thesis, we leverage the collective intelligence of human and computer to tackle several challenges in recommender systems and demonstrate designs of such hybrid systems. We make contributions to the following aspects of recommender systems: providing better new user experience, enhancing topic modeling component for items, composing better recommendation sets and generating personalized natural language explanations. These four applications demonstrate different ways of designing systems with collective intelligence, applicable to domains other than recommender systems. We believe the collective intelligence of human and computer can power more intelligent, user friendly and creative systems, worthy of continuous research effort in future.
@phdthesis{chang_leveraging_2016,
address = {Minneapolis, MN, USA},
title = {Leveraging {Collective} {Intelligence} in {Recommender} {System}},
url = {http://hdl.handle.net/11299/182725},
abstract = {Recommender systems, since their introduction 20 years ago, have been
widely deployed in web services to alleviate user information overload.
Driven by business objectives of their applications, the focus of
recommender systems has shifted from accurately modeling and predicting
user preferences to offering good personalized user experience. The later
is difficult because there are many factors, e.g., tenure of a user,
context of recommendation and transparency of recommender system, that
affect users' perception of recommendations. Many of these factors are
subjective and not easily quantifiable, posing challenges to recommender
algorithms. When pure algorithmic solutions are at their limits in
providing good user experience in recommender systems, we turn to the
collective intelligence of human and computer. Computer and human are
complementary to each other: computers are fast at computation and data
processing and have accurate memory; humans are capable of complex
reasoning, being creative and relating to other humans. In fact, such
close collaborations between human and computer have precedent: after
chess master Garry Kasparov lost to IBM computer ``Deep Blue'', he invited
a new form of chess --- advanced chess, in which human player and a
computer program teams up against such pairs. In this thesis, we leverage
the collective intelligence of human and computer to tackle several
challenges in recommender systems and demonstrate designs of such hybrid
systems. We make contributions to the following aspects of recommender
systems: providing better new user experience, enhancing topic modeling
component for items, composing better recommendation sets and generating
personalized natural language explanations. These four applications
demonstrate different ways of designing systems with collective
intelligence, applicable to domains other than recommender systems. We
believe the collective intelligence of human and computer can power more
intelligent, user friendly and creative systems, worthy of continuous
research effort in future.},
urldate = {2016-11-01},
school = {University of Minnesota},
author = {Chang, Shuo},
month = aug,
year = {2016},
}
Downloads: 0
{"_id":"dPG3Yy9Zetd3FYTpd","bibbaseid":"chang-leveragingcollectiveintelligenceinrecommendersystem-2016","authorIDs":[],"author_short":["Chang, S."],"bibdata":{"bibtype":"phdthesis","type":"phdthesis","address":"Minneapolis, MN, USA","title":"Leveraging Collective Intelligence in Recommender System","url":"http://hdl.handle.net/11299/182725","abstract":"Recommender systems, since their introduction 20 years ago, have been widely deployed in web services to alleviate user information overload. Driven by business objectives of their applications, the focus of recommender systems has shifted from accurately modeling and predicting user preferences to offering good personalized user experience. The later is difficult because there are many factors, e.g., tenure of a user, context of recommendation and transparency of recommender system, that affect users' perception of recommendations. Many of these factors are subjective and not easily quantifiable, posing challenges to recommender algorithms. When pure algorithmic solutions are at their limits in providing good user experience in recommender systems, we turn to the collective intelligence of human and computer. Computer and human are complementary to each other: computers are fast at computation and data processing and have accurate memory; humans are capable of complex reasoning, being creative and relating to other humans. In fact, such close collaborations between human and computer have precedent: after chess master Garry Kasparov lost to IBM computer ``Deep Blue'', he invited a new form of chess — advanced chess, in which human player and a computer program teams up against such pairs. In this thesis, we leverage the collective intelligence of human and computer to tackle several challenges in recommender systems and demonstrate designs of such hybrid systems. We make contributions to the following aspects of recommender systems: providing better new user experience, enhancing topic modeling component for items, composing better recommendation sets and generating personalized natural language explanations. These four applications demonstrate different ways of designing systems with collective intelligence, applicable to domains other than recommender systems. We believe the collective intelligence of human and computer can power more intelligent, user friendly and creative systems, worthy of continuous research effort in future.","urldate":"2016-11-01","school":"University of Minnesota","author":[{"propositions":[],"lastnames":["Chang"],"firstnames":["Shuo"],"suffixes":[]}],"month":"August","year":"2016","bibtex":"@phdthesis{chang_leveraging_2016,\n\taddress = {Minneapolis, MN, USA},\n\ttitle = {Leveraging {Collective} {Intelligence} in {Recommender} {System}},\n\turl = {http://hdl.handle.net/11299/182725},\n\tabstract = {Recommender systems, since their introduction 20 years ago, have been\nwidely deployed in web services to alleviate user information overload.\nDriven by business objectives of their applications, the focus of\nrecommender systems has shifted from accurately modeling and predicting\nuser preferences to offering good personalized user experience. The later\nis difficult because there are many factors, e.g., tenure of a user,\ncontext of recommendation and transparency of recommender system, that\naffect users' perception of recommendations. Many of these factors are\nsubjective and not easily quantifiable, posing challenges to recommender\nalgorithms. When pure algorithmic solutions are at their limits in\nproviding good user experience in recommender systems, we turn to the\ncollective intelligence of human and computer. Computer and human are\ncomplementary to each other: computers are fast at computation and data\nprocessing and have accurate memory; humans are capable of complex\nreasoning, being creative and relating to other humans. In fact, such\nclose collaborations between human and computer have precedent: after\nchess master Garry Kasparov lost to IBM computer ``Deep Blue'', he invited\na new form of chess --- advanced chess, in which human player and a\ncomputer program teams up against such pairs. In this thesis, we leverage\nthe collective intelligence of human and computer to tackle several\nchallenges in recommender systems and demonstrate designs of such hybrid\nsystems. We make contributions to the following aspects of recommender\nsystems: providing better new user experience, enhancing topic modeling\ncomponent for items, composing better recommendation sets and generating\npersonalized natural language explanations. These four applications\ndemonstrate different ways of designing systems with collective\nintelligence, applicable to domains other than recommender systems. We\nbelieve the collective intelligence of human and computer can power more\nintelligent, user friendly and creative systems, worthy of continuous\nresearch effort in future.},\n\turldate = {2016-11-01},\n\tschool = {University of Minnesota},\n\tauthor = {Chang, Shuo},\n\tmonth = aug,\n\tyear = {2016},\n}\n\n","author_short":["Chang, S."],"key":"chang_leveraging_2016","id":"chang_leveraging_2016","bibbaseid":"chang-leveragingcollectiveintelligenceinrecommendersystem-2016","role":"author","urls":{"Paper":"http://hdl.handle.net/11299/182725"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"phdthesis","biburl":"https://api.zotero.org/users/6655/collections/TJPPJ92X/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","creationDate":"2020-03-27T02:34:35.366Z","downloads":0,"keywords":[],"search_terms":["leveraging","collective","intelligence","recommender","system","chang"],"title":"Leveraging Collective Intelligence in Recommender System","year":2016,"dataSources":["5Dp4QphkvpvNA33zi","jfoasiDDpStqkkoZB","BiuuFc45aHCgJqDLY"]}