7,476 Hits in 4.9 sec

Tag propagation based recommendation across diverse social media

Deqing Yang, Yanghua Xiao, Yangqiu Song, Junjun Zhang, Kezun Zhang, Wei Wang
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
Since many social media have rich tags on both items or users, tag-based profiling became popular for recommendation.  ...  However, most previous recommendation approaches have low effectiveness in handling sparse data or matching tags from different social media.  ...  We found that the tags generated in different social media are often hard to be matched blocking tag-based recommendation between users and items across different domains.  ... 
doi:10.1145/2567948.2577285 dblp:conf/www/YangXSZZ014 fatcat:ckizwj6rwfgv7albec6yezzsse

Hybrid social media network

Dong Liu, Guangnan Ye, Ching-Ting Chen, Shuicheng Yan, Shih-Fu Chang
2012 Proceedings of the 20th ACM international conference on Multimedia - MM '12  
, tags, etc).  ...  In this paper, we develop a hybrid social media network, through which the heterogeneous entities and relations are seamlessly integrated and a joint inference procedure across the heterogeneous entities  ...  The work in [8] employed the hypergraph to model the multi-typed objects including documents, tags and users, based on which a personalized tag recommendation task is cast into a graph based ranking  ... 
doi:10.1145/2393347.2393438 dblp:conf/mm/LiuYCYC12 fatcat:gncqk24wsjewpiqi5og5rqgp6q

Contextual wisdom

Amit Zunjarwad, Hari Sundaram, Lexing Xie
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
Events refer to real-world phenomena that occur at a specific time and place, and media and text tags are treated as facets of the event metadata.  ...  For a specific media instance to be annotated, we start the process from an initial query vector and the optimal recommendations are determined by using a coupling strategy between the global similarity  ...  For the social network based annotation, we combined all the co-occurrence matrixes across the social network using uniform trustthis is equivalent to the case that everyone in the network is equally trustworthy  ... 
doi:10.1145/1291233.1291382 dblp:conf/mm/ZunjarwadSX07 fatcat:2r44h4ceffb45lv4xt3jzbbjte

Do Recommender Systems Make Social Media More Susceptible to Misinformation Spreaders?

Antonela Tommasel, Filippo Menczer
2022 Sixteenth ACM Conference on Recommender Systems  
However, recommenders could also (unintendedly) help propagate misinformation and increase the social influence of the spreading it.  ...  In this context, we study the impact of friend recommender systems on the social influence of misinformation spreaders on Twitter.  ...  For each metric, we report the average across all users and the standard deviation. Diversity and novelty for the base graph were computed considering the test set as the recommended users.  ... 
doi:10.1145/3523227.3551473 fatcat:g6qwseio3rfjxgkf6gnb5ivcfa

User Identity Linkage across Online Social Networks

Kai Shu, Suhang Wang, Jiliang Tang, Reza Zafarani, Huan Liu
2017 SIGKDD Explorations  
The increasing popularity and diversity of social media sites has encouraged more and more people to participate on multiple online social networks to enjoy their services.  ...  User identity linkage across online social networks is an emerging task in social media and has attracted increasing attention in recent years.  ...  However, the task of linking users accounts on multiple social media sites, also called user identity linkage, is a challenging task because: (1) user identity information can be rather diverse across  ... 
doi:10.1145/3068777.3068781 fatcat:zuh6dpjzarcf3ftbdx7k7o6wqy

What Are You Known For?

Cheng Cao, Hancheng Ge, Haokai Lu, Xia Hu, James Caverlee
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
User interests and expertise are valuable but o en hidden resources on social media.  ...  For example, Twi er Lists and LinkedIn's Skill Tags provide a partial perspective on what users are known for (by aggregating crowd tagging knowledge), but the vast majority of users are untagged; their  ...  For social media research, the latent factor model is a state-of-theart method for user recommendation.  ... 
doi:10.1145/3077136.3080820 dblp:conf/sigir/CaoGLHC17 fatcat:naklexxzd5al7bwyoosxsoggsy

Building Your Own Reading List Anytime via Embedding Relevance, Quality, Timeliness and Diversity

Bo-Wen Zhang, Xu-Cheng Yin, Fang Zhou, Jian-Lin Jin
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
(of results) are embedded into vector representations respectively based on user-generated contents and statistics on social media.  ...  During every summer holidays, several editions of reading lists are recommended and emerged on mass media, e.g., New York Times, and BBC.  ...  Social media opened up new horizons for book recommendations.  ... 
doi:10.1145/3077136.3080734 dblp:conf/sigir/ZhangYZJ17 fatcat:dkaah7ky4ferniun7alhy3saey

Learning to Hash-tag Videos with Tag2Vec [article]

Aditya Singh, Saurabh Saini, Rajvi Shah, PJ Narayanan
2016 arXiv   pre-print
Recently, a new type of labeling mechanism known as hash-tags have become increasingly popular on social media sites.  ...  Traditional data-driven approaches for tag enrichment and recommendation use direct visual similarity for label transfer and propagation.  ...  These media sites allow users to upload, tag, and share their content with a wide audience across the world.  ... 
arXiv:1612.04061v1 fatcat:l45mrdvnc5a67ac4xkhmozkvq4

New grand challenge for multimedia information retrieval: bridging the utility gap

Alan Hanjalic
2012 International Journal of Multimedia Information Retrieval  
Then, some possibilities for realizing the utility-by-design approach will be highlighted and translated into a number of recommended research directions.  ...  Based on the analysis of the lists of candidate tags collected from the images from other collections that share the original tags from the first image, new related tags can automatically propagate to  ...  Two original tags assigned to the first image by User 1 are enriched by new tags implicitly recommended by Users 2 and 3 based on the analysis of the lists of candidate tags collected from the images that  ... 
doi:10.1007/s13735-012-0019-z fatcat:adhutbvjivbszlnqqpkdetfv5q

Systematic Evaluation of Social Recommendation Systems: Challenges and Future

Priyanka Rastogi, Dr. Vijendra
2016 International Journal of Advanced Computer Science and Applications  
This paper discusses reasons for evolution of recommender systems leading to transition from traditional to social information based recommendations.  ...  Social Recommender System (SRS) exploits social contextual information in the form of social links of users, social tags, user-generated data that contain huge supplemental information about items or services  ...  ., and He, X (2011) proposed music recommendation hypergraph (MRH) algorithm wherein they incorporated various kinds of social media based information and music acoustic-based content.  ... 
doi:10.14569/ijacsa.2016.070420 fatcat:wwvyumdr5ffohiphirbb3ycuoa

Mining expertise and interests from social media

Ido Guy, Uri Avraham, David Carmel, Sigalit Ur, Michal Jacovi, Inbal Ronen
2013 Proceedings of the 22nd international conference on World Wide Web - WWW '13  
Social media data can be very useful for expertise mining due to the variety of existing applications, the rich metadata, and the diversity of user associations with content.  ...  We distinguish between two semantics that relate a user to a topic: expertise in the topic and interest in it and compare these two semantics across the different social media applications.  ...  This analysis strives to understand the diversity of our data and the potential value of collecting and aggregating expertise data across a wide variety of social media applications.  ... 
doi:10.1145/2488388.2488434 dblp:conf/www/GuyACUJR13 fatcat:v2da5tv5dzgndkqiw4kz3x3rzu

A Survey on Decision Support Systems in Social Media

M. Thangaraj, R. Indra
2015 International Journal of Computer Applications Technology and Research  
Recommendations in social web are used to personalize the web [20] . Social Tagging System is one type of social media.  ...  In this paper we present the survey of various recommendations in Social Tagging Systems (STSs) like tag, item, user and unified recommendations along with semantic web and also discussed about major thrust  ...  Social Semantic Cloud of Tags (SCOT) aims to describe folksonomic characteristics and to offer social interoperability of semantic tag data across heterogeneous sources.  ... 
doi:10.7753/ijcatr0409.1008 fatcat:zguexhxslvexxfpzdnnr2r4uma

Exploring the affordances of Social Network sites: an Analysis of Three Networks

Sheila O'Riordan, Joseph Feller, Tadhg Nagle
2012 European Conference on Information Systems  
The study reveals a diverse collection of software features which afford user behaviour in six areas of activity: social connectivity, social interactivity, profile management, content discovery, content  ...  Social network sites (SNS) are becoming increasingly important, both for individuals and organizations.  ...  YouTube's homepage includes recommendations and the ability to explore content based on genre or topic.  ... 
dblp:conf/ecis/ORiordanFN12 fatcat:2ygwqksrxrbp3gcf4x3nour4y4

Social Media and Microblogs Credibility: Identification, Theory Driven Framework, and Recommendation

Khubaib Ahmed Qureshi, Rauf Ahmed Shams Malick, Muhammad Sabih
2021 IEEE Access  
Social media microblogs are extensively used to get news and other information. It brings the real challenge to distinguish that what particular information is credible.  ...  The framework is generic to social media and specifically implemented for microblogs. It is completely transformed up to features level, in the context of microblogs.  ...  /Valance, Consensus Social media based credible marketing related electronic word of mouth (eWOM) framework is proposed based on research theories.  ... 
doi:10.1109/access.2021.3114417 fatcat:nawg5fgd55fyxcriho3urlxwoq

Affective Contextual Mobile Recommender System

Chao Wu, Jia Jia, Wenwu Zhu, Xu Chen, Bowen Yang, Yaoxue Zhang
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
To capture this effect, in this paper we propose Kaleido, a real mobile system to achieve an affect-aware learning-based social media recommendation.  ...  Exponential growth of media consumption in online social networks demands effective recommendation to improve the quality of experience especially for on-the-go mobile users.  ...  The volume and diversity of data also reflects the real-life behavior of the participant users, which is crucial for understanding and recommending media in mobile social application network traffic, and  ... 
doi:10.1145/2964284.2964327 dblp:conf/mm/WuJZCYZ16 fatcat:aktobty4pbhvzpcv2lhg4xiuzy
« Previous Showing results 1 — 15 out of 7,476 results