Answering search queries with CrowdSearcher

Abstract

Web users are increasingly relying on social interaction to complete and validate the results of their search activities. While search systems are superior machines to get world-wide information, the opinions collected within friends and expert/local communities can ultimately determine our decisions: human curiosity and creativity is often capable of going much beyond the capabilities of search systems in scouting "interesting" results, or suggesting new, unexpected search directions. Such personalized interaction occurs in most times aside of the search systems and processes, possibly instrumented and mediated by a social network; when such interaction is completed and users resort to the use of search systems, they do it through new queries, loosely related to the previous search or to the social interaction. In this paper we propose CrowdSearcher, a novel search paradigm that embodies crowds as first-class sources for the information seeking process. CrowdSearcher aims at filling the gap between generalized search systems, which operate upon world-wide information - including facts and recommendations as crawled and indexed by computerized systems - with social systems, capable of interacting with real people, in real time, to capture their opinions, suggestions, emotions. The technical contribution of this paper is the discussion of a model and architecture for integrating computerized search with human interaction, by showing how search systems can drive and encapsulate social systems. In particular we show how social platforms, such as Facebook, LinkedIn and Twitter, can be used for crowdsourcing search-related tasks; we demonstrate our approach with several prototypes and we report on our experiment upon real user communities

Modeling, Modeling, Modeling: From Web to Enterprise to Crowd to Social

“…A that time, we developed CrowdSearcher, a model and tool for engaging crowds in the context of search queries [3]. Our complete paradigm, illustrated in Fig.…”

“…In other cases, however, 3M has been a successful vehicle for commercialization and standardization. Our work is traced by papers that appeared at WWW Conferences of the period, dedicated to WebML [17], to liquid queries over search services [4], to crowd-based search [3] and to knowledge extraction for social sources [9].…”

NoXperanto: Crowdsourced Polyglot Persistence

“…There exists equivalent works which consider a unified language, proposing some SQL extension [10,15,3,7,11], or consider a metamodel approache such as the Apache's MetaModel project 2 . To overcome existing problems of data integration, we propose a solution to exploit a crowd of experts in a transparent way.…”

“…We do not assume having a unified query language, but rather we follow the idea of the polyglot persistence movement to support multiple languages. The idea of using crowdsourcing for answering queries over a database has been covered in previous works [15,3,16,7,9,11,5]. In particular, CrowdDB [9] integrates human inputs within a query plan that contains operations that usual database systems cannot always answer correctly (i.e.…”

Tell Me What You Like and I’ll Tell You What You Are: Discriminating Visual Preferences on Flickr Data

“…those visual preferences that distinguish people from each other. In particular, we take a crowdsearch approach [13] and we focus on Flickr 1 , a popular website where every user can select his/her preferred photos, by tagging them as "favorites". This creates, for every user, a set of favorite photos, which is often very heterogeneous and whose modeling/recognition goes beyond standard computer vision tasks such as object/scene recognition (see fig.…”