The influence of user profile enrichment on buzz spread in social media experiments on delicious

The influence of user profile enrichment on buzz spread in social media experiments on delicious

Manel Mezghani André Péninou Florence Sèdes Sirinya On-At Arnaud Quirin Marie-Françoise Canut

Université de Sfax, laboratoire MIRACL, Sfax, Tunisie

IRIT, Université de Toulouse, CNRS, INPT, UPS, UT1, UT2J, France

Corresponding Author Email: 
{mezghani.manel, aquirin}@gmail.com, {andre.peninou, florence.sedes, sirinya.on-at}@irit.fr, marie-francoise.canut@univ-tlse2.fr
Page: 
67-81
|
DOI: 
https://doi.org/10.3166/ISI.21.4.67-81
Received: 
N/A
| |
Accepted: 
N/A
| | Citation
Abstract: 

The user is the main contributor for creating information in social media and is influenced by the information shared through such networks. There are so-called “buzz”, which is a technique to cause a stir around a piece of information (fact or rumour) so that several users will be interested in simultaneously, can be defined as a popular piece of information in a specific time. We are interested in studying the influence of the dynamic user profile enrichment (Mezghani et al., 2014) on the buzz propagation and we experiment it to the social network Delicious. Delicious contains social annotations (tags) provided by users and that contribute to influence other users to follow some information or to use them. Our study is grounded on the following methodology: 1) we analyse the propagation of tags considered as buzz through time 2) we apply the dynamic user profile enrichment and we analyse the influence of this enrichment in the buzz propagation, 3) we analyse if the enrichment approach anticipates the buzz propagation. Thus, we show interest, during profile enrichment, of filtering the information in order to propose relevant results to the user and avoid “bad” recommendations.

Keywords: 

user profile, enrichment, tag, resource, buzz, time

1. Introduction
2. Aperçu de l’approche d’enrichissement dynamique
3. Étude de cas sur un ensemble de données de Delicious sur la propagation de buzz
4. Conclusion
Remerciements
  References

Cantador I., Brusilovsky P., Kuflik T. (2011). 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011), Proceedings of the 5th ACM conference on Recommender systems (RecSys’11), ACM, New York, NY, USA.

Hashimoto T., Kuboyama T., Shirota Y. (2011) Rumor analysis framework in social media, TENCON 2011-2011 IEEE Region 10 Conference, p. 133-137.

Joly A., Maret P., Daigremont J. (2010). Contextual recommendation of social updates, a tagbased framework. In Proceedings of the 6th International Conference on Active Media Technology, AMT’10, p. 436-447, Berlin, Heidelberg. Springer-Verlag.

Kim H.-N., Alkhaldi A., El Saddik A., Jo G.-S. (2011). Collaborative user modeling with user-generated tags for social recommender systems. Expert Systems with Applications. vol. 38, n° 7, p. 8488-8496.

Manzat A., Grigoras R., Sèdes F. (2010). Towards a User-aware Enrichment of Multimedia Metadata, Workshop on Semantic Multimedia Database Technologies (SMDT’10), Saarbrcken, Germany, vol. 680, CEUR Workshop Proceedings, p. 30-41.

Meo P. D., Ferrara E., Abel F., Aroyo L., Houben G.-J. (2014). Analyzing user behavior across social sharing environments. ACM Transactions on Intelligent Systems and Technology (TIST), vol 5, n° 1, p. 14, 2013, ACM.

Mezghani M., Zayani C-A., Amous I., Péninou A., Sèdes F. (2014). Dynamic Enrichment of Social Users’ Interests. IEEE Eighth International Conference on Research Challenges in Information Science (RCIS’14). IEEE, p. 1-11.

Rosnow R.L., Kimmel A.J. (2000). Rumor. Encyclopedia of Psychology, vol. 7, edited by A.E. Kazdin. New York: Oxford University Press, p. 122-123.

Tchuente D., Canut M.-F., Jessel N., Peninou A., Sedes F. (2013). A community-based algorithm for deriving users’ profiles from egocentrics networks : experiment on facebook and DBLP. Social Network Analysis and Mining, vol. 3, n° 3, p. 667-683.

Zheng N., Li Q. (2011). A recommender system based on tag and time informa- tion for social tagging systems. Expert Syst. Appl., vol. 38, n° 4, p. 4575-4587.