In this paper we investigate whether it is possible to create a computational approach that allows us to distinguish topical tags (i.e. talking about the topic of a resource) and non-topical tags (i.e. describing aspects of a resource that are not related to its topic) in folksonomies, in a way that correlates with humans. Towards this goal, we collected 21 million tags (1.2 million unique terms) from Delicious and developed an unsupervised statistical algorithm that classifies such tags by applying a word space model adapted to the folksonomy space. Our algorithm analyses the co-occurrence network of tags to a target tag and exploits graph-based metrics for their classification. We validated its outcomes against a reference classification made by humans on a limited number of terms in three separate tests. The analysis of the outcomes of our algorithm shows, in some cases, a consistent disagreement among humans and between humans and our algorithm about what constitutes a topical tag, and suggests the rise of a new category of overly generic tags (i.e. umbrella tags).
BatesJRowleyJ. Social reproduction and exclusion in subject indexing: A comparison of public library OPACs and LibraryThing folksonomy. Journal of Documentation2011; 67(3): 431–448; doi: 10.1108/00220411111124532
3.
GuinardDTrifaV. Towards the Web of things: Web mashups for embedded devices. In: Proceedings of the 2nd workshop on mashups, enterprise mashups and lightweight composition on the Web (MEM 2009), http://integror.net/mem2009/papers/paper4.pdf (2009, accessed 20 March 2015).
4.
HendlerJShadboltNHallWBerners-LeeTWeitznerD. Web science: An interdisciplinary approach to understanding the Web. Communications of the ACM2008; 51(7): 60–69; doi: 10.1145/1364782.1364798
5.
De MeoPNoceraATerracinaGUrsinoD. Recommendation of similar users, resources and social networks in a social internetworking scenario. Information Sciences2011; 181(7): 1285–1305; doi: 10.1016/j.ins.2010.12.001
6.
BellogínACantadorICastellsP. A comparative study of heterogeneous item recommendations in social systems. Information Sciences2013; 221: 142–169; doi: 10.1016/j.ins.2012.09.039
7.
KippMEI. @toread and cool: Subjective, affective and associative factors in tagging. In: Proceedings of the 36th annual conference of the Canadian Association for Information Science (CAIS 2008), http://www.cais-acsi.ca/proceedings/2008/kipp_2008.pdf (2008, accessed 20 March 2015).
8.
CatarinoMEBaptistaAA. Relating folksonomies with Dublin Core. In: Proceedings of the 2008 DCMI international conference on Dublin Core and metadata applications (DC 2008), http://dcpapers.dublincore.org/pubs/article/view/915/911 (2008, accessed 20 March 2015).
9.
GolderSHubermanB. Usage patterns of collaborative tagging systems. Journal of Information Science2006; 32(2): 198–208; doi: 10.1177/0165551506062337
StrohmaierMKornerCKernR. Understanding why users tag: A survey of tagging motivation literature and results from an empirical study. Web Semantics: Science, Services and Agents on the World Wide Web2012; 17: 1–11; doi: 10.1016/j.websem.2012.09.003
12.
BaptistaAATonkinELResminiAVan HoolandSPinheiroSMendezE. Kinds of tags – Progress report for the DC-Social Tagging Community, podcast presentation at the 2007 International Conference on Dublin Core and Metadata Applications (DC 2007), http://hdl.handle.net/1822/6881 (2007, accessed 20 March 2015).
13.
Dublin Core Metadata Initiative. Dublin Core Metadata Element Set, Version 1.1, DCMI Recommendation, 14 June 2012, http://dublincore.org/documents/dces/ (2012, accessed 20 March 2015).
14.
SenSLamSKRashidAMCosleyDFrankowskiDOsterhouseJHarperFMRiedlJ. Tagging, communities, vocabulary, evolution. In: Proceedings of the 2006 ACM conference on computer supported cooperative work (CSCW 2006), 1st edn.New York: ACM, 2006, pp. 181–190; doi: 10.1145/1180875.1180904
15.
GuptaMLiRYinZHanJ. Survey on social tagging techniques. ACM SIGKDD Explorations Newsletter2010; 12(1): 58–72; doi: 10.1145/1882471.1882480
16.
HutchinsWJ. On the problem of ‘aboutness’ in document analysis. Journal of Informatics1977; 1(1): 17–35.
17.
YangLSunTZhangMMeiQ. We know what @you #tag: Does the dual role affect hashtag adoption? In: Proceedings of the 21st international conference on World Wide Web (WWW 2012), 1st edn.New York: ACM, 2012, pp. 261–270; doi: 10.1145/2187836.2187872
18.
MikaP. Ontologies are us: A unified model of social networks and semantics. Web Semantics: Science, Services and Agents on the World Wide Web2006; 5: 5–15; doi: 10.1016/j.websem.2006.11.002
19.
SpeciaLMottaE. Integrating folksonomies with the Semantic Web. In: FranconiEKiferMMayW (eds) Proceedings of the 4th European Semantic Web conference (ESWC 2007), 1st edn.Berlin: Springer, 2007, pp. 624–639; doi: 10.1007/978–3–540–72667–8_44
YiKChanLM. Linking folksonomy to Library of Congress subject headings: An exploratory study. Journal of Documentation2009; 65(6): 872–900; doi: 10.1108/00220410910998906
22.
GuarinoNWeltyC. Evaluating ontological decisions with OntoClean. Communications of the ACM2002; 45(2): 61–65; doi: 10.1145/503124.503150
23.
PalmaRZablithFHaasePCorchoO. Ontology evolution. In: Suárez-FigueroaMCGómez-PérezAMottaEGangemiA (eds) Ontology Engineering in a Networked World, 1st edn.Berlin: Springer, 2012, pp. 235–255; doi: 10.1007/978–3–642–24794–1_11
24.
ZablithFSabouMd’AquinMMottaE. Ontology evolution with Evolva. In: AroyoL. (eds) Proceedings of the 6th European Semantic Web conference (ESWC 2009), 1st edn.Berlin: Springer, 2009, pp. 908–912; doi: 10.1007/978–3–642–02121–3_80
25.
DeerwesterSDumaisSTFurnasGWLandauerTKHarshmanR. Indexing by latent semantic analysis. Journal of the American Society for Information Science1990; 41(6): 391–407; doi: 10.1002/(SICI)1097–4571(199009)41:6<391::AID-ASI1>3.0.CO;2–9
26.
BurgessCLundK. Modelling parsing constraints with high-dimensional context space. Language and Cognitive Processes1997; XII: 1–3; doi: 10.1080/016909697386844
TurneyPDPantelP. From frequency to meaning: Vector space models of semantics. Journal of Artificial Intelligence Research2010; 37: 141–188; doi: 10.1613/jair.2934
29.
WiddowsD. Geometry and meaning, 1st edn.Stanford, CA: CSLI, 2004.
DorowBWiddowsDLingKEckmannJPSergiDMosesE. Using curvature and Markov clustering in graphs for lexical acquisition and word sense discrimination, http://arxiv.org/pdf/condmat/0403693.pdf (2004, accessed 20 March 2014).
33.
MillerGA. WordNet: A lexical database for English. Communications of the ACM1995; 38(11): 39–41; doi: 10.1145/219717.219748
34.
HalpinHRobuVShepherdH. The complex dynamics of collaborative tagging. In: Proceedings of 16th international World Wide Web Conference (WWW 2007). New York: ACM, 2007, pp. 211–220; doi: 10.1145/1242572.1242602
35.
MonclarRTeclaAOliveiraJde SouzaJM. MEK: Using spatial–temporal information to improve social networks and knowledge dissemination. Information Sciences2009; 179(15): 2524–2537; doi: 10.1016/j.ins.2009.01.032
De MeoPQuattroneGUrsinoD. Exploitation of semantic relationships and hierarchical data structures to support a user in his annotation and browsing activities in folksonomies. Information Systems2009; 34(6): 511–535; doi: 10.1016/j.is.2009.02.004
38.
BegMMSAhmadN. Web search enhancement by mining user actions. Information Sciences2006; 177(23): 5203–5218; doi: 10.1016/j.ins.2006.06.011
