Internet User Advice Based On Collaborative Screening And Voting

VAGLE VISHAL KUMAR, SANDEEP AGARWALLA, Dr. M. SAMBASIVUDU

Abstract


The option to vote on different social issues is a feature that has just recently been added to several social media sites. In the context of this question, there are fresh challenges and opportunities for counsel. In this study, we create a suite of recommender systems (RS) to mine users' social networks and group memberships in order to deliver social voting suggestions. We do this by using matrix factorization (MF) and nearest-neighbor (NN). We show that including information about social networks and group membership significantly improves the accuracy of popularity-based vote suggestions, with the former dominating the latter in NN-based methods. This was demonstrated by using data from social votes cast in the real world in experimental settings. In addition, we find that social and group information is valuable to light users to a greater degree than it is to heavy users. Experimentally, we observed that simple meta-path-based NN models performed better than computationally complicated MF models when it came to proposing hot votes. On the other hand, MF models performed better when it came to mining users' interests for cold votes. In addition, we recommend a hybrid RS, which is a combination of several distinct research strategies, in order to get the greatest possible amount of top-k hits.

References


R. M. Bond et al., “A 61-million-person experiment in social influence and political mobilization,” Nature, vol. 489, pp. 295–298, Sep. 2012.

G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions,” IEEE Trans. Knowl. Data Eng., vol. 17, no. 6, pp. 734–749, Jun. 2005.

X. Su and T. M. Khoshgoftaar, “A survey of collaborative filtering techniques,” Adv. Artif. Intell., vol. 2009, Aug. 2009, Art. no. 421425, doi: 10.1155/2009/421425.

Y. Koren, “Factorization meets the neighborhood: A multifaceted collaborative filtering model,” in Proc. ACM KDD, 2008, pp. 426–434.

Y. Koren, “Collaborative filtering with temporal dynamics,” in Proc. KDD, Paris, France, 2009, pp. 447–456.

A. Paterek, “Improving regularized singular value decomposition for collaborative filtering,” in Proc. KDDCup, 2007, pp. 39–42.

R. Salakhutdinov and A. Mnih, “Probabilistic matrix factorization,” in Proc. NIPS, vol. 20. 2008, pp. 1257–1264.

K. Yu, A. Schwaighofer, V. Tresp, X. Xu, and H. P. Kriegel, “Probabilistic memory-based collaborative filtering,” IEEE Trans. Knowl. Data Eng., vol. 16, no. 1, pp. 56–69, Jan. 2004.

R. H. Keshavan, A. Montanari, and S. Oh, “Matrix completion from noisy entries,” J. Mach. Learn. Res., vol. 11, pp. 2057–2078, Jul. 2010.

P. Cremonesi, Y. Koren, and R. Turrin, “Performance of recommender algorithms on top-N recommendation tasks,” in Proc. ACM RecSys, 2010, pp. 39–46.


Full Text: PDF

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Copyright © 2012 - 2023, All rights reserved.| ijitr.com

Creative Commons License
International Journal of Innovative Technology and Research is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJITR , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.