Information Foraging Theory as a Form of Collective Intelligence for Social Search
L. Luca, B. Stephen, and D. Pierpaolo. Computational Collective Intelligence: Semantic Web, Social Networks and Multiagent Systems First International Conference, ICCCI 2009, Wroclaw, Poland, volume 5796 of Lecture Notes in Artificial Intelligence, Springer, Berlin, (2009)
DOI: 10.1007/978-3-642-04441-0_5
Abstract
The World Wide Web is growing in size and with the proliferation of large-scale collaborative computing environments Social search has become increasingly important. The focal point of this recent field is to assign relevance and trustworthiness to web-pages by taking into account the reader's perspective rather than web-masters' point of view. Current web-searching technologies tend to rely on explicit human recommendations, in part because it is hard to obtain user' feedback however these methods are hard to scale. Implicit feedback techniques are a potentially useful alternative. The challenge is in producing implicit web-rankings by reasoning over users' activity during a web-search but without recourse to explicit human intervention. This paper focuses on a novel Social Search formal model based on Information Foraging Theory, showing a different way to implicitly judge web entities by considering effort expended by users in viewing them. 100 university students were recruited to explicitly evaluate the usefulness of 12 thematic web-sites and an experiment was performed implicitly gathering their web-browsing activity. Correlation indexes were adopted and encouraging results where obtained suggesting the existence of a considerable relationship between explicit feedback and implicit derived judgements. Furthermore, a comparison of the results obtained and the results provided by Google was performed. The proposed nature-inspired approach shows that, by considering the same searching query, Social search to be more effective than the Google Page-Rank Algorithm. This evidence supports the presentation of a novel general schema for a Social search engine generating implicit web-rankings by taking into account the Collective Intelligence emerged from users by reasoning on their behaviour.
Computational Collective Intelligence: Semantic Web, Social Networks and Multiagent Systems First International Conference, ICCCI 2009, Wroclaw, Poland
%0 Book Section
%1 LucaStephenPierpaolo09ICCCI
%A Luca, Longo
%A Stephen, Barrett
%A Pierpaolo, Dondio
%B Computational Collective Intelligence: Semantic Web, Social Networks and Multiagent Systems First International Conference, ICCCI 2009, Wroclaw, Poland
%C Berlin
%D 2009
%E Nguyen, Ngoc Thanh
%E Kowalczyk, Ryszard
%E Chen, Shyi-Ming
%I Springer
%K v1500 springer paper ai semantic web search social software information architecture zzz.hci
%P 63-74
%R 10.1007/978-3-642-04441-0_5
%T Information Foraging Theory as a Form of Collective Intelligence for Social Search
%V 5796
%X The World Wide Web is growing in size and with the proliferation of large-scale collaborative computing environments Social search has become increasingly important. The focal point of this recent field is to assign relevance and trustworthiness to web-pages by taking into account the reader's perspective rather than web-masters' point of view. Current web-searching technologies tend to rely on explicit human recommendations, in part because it is hard to obtain user' feedback however these methods are hard to scale. Implicit feedback techniques are a potentially useful alternative. The challenge is in producing implicit web-rankings by reasoning over users' activity during a web-search but without recourse to explicit human intervention. This paper focuses on a novel Social Search formal model based on Information Foraging Theory, showing a different way to implicitly judge web entities by considering effort expended by users in viewing them. 100 university students were recruited to explicitly evaluate the usefulness of 12 thematic web-sites and an experiment was performed implicitly gathering their web-browsing activity. Correlation indexes were adopted and encouraging results where obtained suggesting the existence of a considerable relationship between explicit feedback and implicit derived judgements. Furthermore, a comparison of the results obtained and the results provided by Google was performed. The proposed nature-inspired approach shows that, by considering the same searching query, Social search to be more effective than the Google Page-Rank Algorithm. This evidence supports the presentation of a novel general schema for a Social search engine generating implicit web-rankings by taking into account the Collective Intelligence emerged from users by reasoning on their behaviour.
@incollection{LucaStephenPierpaolo09ICCCI,
abstract = {The World Wide Web is growing in size and with the proliferation of large-scale collaborative computing environments Social search has become increasingly important. The focal point of this recent field is to assign relevance and trustworthiness to web-pages by taking into account the reader's perspective rather than web-masters' point of view. Current web-searching technologies tend to rely on explicit human recommendations, in part because it is hard to obtain user' feedback however these methods are hard to scale. Implicit feedback techniques are a potentially useful alternative. The challenge is in producing implicit web-rankings by reasoning over users' activity during a web-search but without recourse to explicit human intervention. This paper focuses on a novel Social Search formal model based on Information Foraging Theory, showing a different way to implicitly judge web entities by considering effort expended by users in viewing them. 100 university students were recruited to explicitly evaluate the usefulness of 12 thematic web-sites and an experiment was performed implicitly gathering their web-browsing activity. Correlation indexes were adopted and encouraging results where obtained suggesting the existence of a considerable relationship between explicit feedback and implicit derived judgements. Furthermore, a comparison of the results obtained and the results provided by Google was performed. The proposed nature-inspired approach shows that, by considering the same searching query, Social search to be more effective than the Google Page-Rank Algorithm. This evidence supports the presentation of a novel general schema for a Social search engine generating implicit web-rankings by taking into account the Collective Intelligence emerged from users by reasoning on their behaviour.},
added-at = {2012-05-30T10:50:17.000+0200},
address = {Berlin},
author = {Luca, Longo and Stephen, Barrett and Pierpaolo, Dondio},
biburl = {https://www.bibsonomy.org/bibtex/282aea2daa9be1826df1a746ac1c3a947/flint63},
booktitle = {Computational Collective Intelligence: Semantic Web, Social Networks and Multiagent Systems First International Conference, ICCCI 2009, Wroclaw, Poland},
crossref = {ICCCI2009},
doi = {10.1007/978-3-642-04441-0_5},
editor = {Nguyen, Ngoc Thanh and Kowalczyk, Ryszard and Chen, Shyi-Ming},
file = {SpringerLink:2009/LucaStephenPierpaolo09ICCCI.pdf:PDF},
groups = {public},
interhash = {377c31fdfc3b336daf02387c1a0f0a54},
intrahash = {f527c7b39529e6d1269dd3069ad2fa38},
keywords = {v1500 springer paper ai semantic web search social software information architecture zzz.hci},
pages = {63-74},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
timestamp = {2015-03-05T14:13:15.000+0100},
title = {Information Foraging Theory as a Form of Collective Intelligence for Social Search},
username = {flint63},
volume = 5796,
year = 2009
}