Results 11 -
19 of
19
The Joint Inference of Topic Diffusion and Evolution in Social Communities
"... Abstract—The prevalence of Web 2.0 techniques has led to the boom of various online communities, where topics spread ubiquitously among user-generated documents. Working together with this diffusion process is the evolution of topic content, where novel contents are introduced by documents which ado ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—The prevalence of Web 2.0 techniques has led to the boom of various online communities, where topics spread ubiquitously among user-generated documents. Working together with this diffusion process is the evolution of topic content, where novel contents are introduced by documents which adopt the topic. Unlike explicit user behavior (e.g., buying a DVD), both the diffusion paths and the evolutionary process of a topic are implicit, making their discovery challenging. In this paper, we track the evolution of an arbitrary topic and reveal the latent diffusion paths of that topic in a social community. A novel and principled probabilistic model is proposed which casts our task as an joint inference problem, which considers textual documents, social influences, and topic evolution in a unified way. Specifically, a mixture model is introduced to model the generation of text according to the diffusion and the evolution of the topic, while the whole diffusion process is regularized with user-level social influences through a Gaussian Markov Random Field. Experiments on both synthetic data and real world data show that the discovery of topic diffusion and evolution benefits from this joint inference; and the probabilistic model we propose performs significantly better than existing methods. I.
Science
"... The prevalence of social media has sparked novel adver-tising models, vastly different from the traditional keyword based bidding model adopted by search engines. One such model is topic based advertising, popular with micro-blogging sites. Instead of bidding on keywords, the approach is based on bi ..."
Abstract
- Add to MetaCart
The prevalence of social media has sparked novel adver-tising models, vastly different from the traditional keyword based bidding model adopted by search engines. One such model is topic based advertising, popular with micro-blogging sites. Instead of bidding on keywords, the approach is based on bidding on topics, with the winning bid allowed to dis-seminate messages to users interested in the specific topic. Naturally topics have varying costs depending on multiple factors (e.g., how popular or prevalent they are). Similarly users in a micro-blogging site have diverse interests. As-suming one wishes to disseminate a message to a set V of users interested in a specific topic, a question arises whether it is possible to disseminate the same message by bidding on a set of topics that collectively reach the same users in V albeit at a cheaper cost. In this paper, we show how an alternative set of topics R with a lower cost can be identified to target (most) users in V. Two approximation algorithms are presented to address the problem with strong bounds. We propose techniques based on pruning and approximate calculations to speed up the execution of these algorithms while maintaining guaran-teed approximation bounds. Theoretical analysis and exten-sive quantitative and qualitative experiments over real-world data sets at realistic scale containing millions of users and topics demonstrate the effectiveness of our approach.
Price Trade-offs in Social Media Advertising
"... The prevalence of social media has sparked novel advertising mod-els, vastly different from the traditional keyword based bidding model adopted by search engines. One such model is topic based advertising, popular with micro-blogging sites. Instead of bidding ..."
Abstract
- Add to MetaCart
(Show Context)
The prevalence of social media has sparked novel advertising mod-els, vastly different from the traditional keyword based bidding model adopted by search engines. One such model is topic based advertising, popular with micro-blogging sites. Instead of bidding
Cognos: Crowdsourcing Search for Topic Experts in Microblogs
"... Finding topic experts on microblogging sites with millions of users, such as Twitter, is a hard and challenging problem. In this paper, we propose and investigate a new method-ology for inferring topical experts in the popular Twitter social network. Our methodology relies on the wisdom of the Twitt ..."
Abstract
- Add to MetaCart
(Show Context)
Finding topic experts on microblogging sites with millions of users, such as Twitter, is a hard and challenging problem. In this paper, we propose and investigate a new method-ology for inferring topical experts in the popular Twitter social network. Our methodology relies on the wisdom of the Twitter crowds – it leverages Twitter Lists, which are often carefully created by individual users to include ex-perts on topics that interest them and whose meta-data (List names and descriptions) provide valuable semantic cues to experts ’ domain of expertise. We mined List information to build Cognos, an expert search system for Twitter. Detailed experimental evaluation based on a real-world deployment shows that: (a) Cognos infers a user’s expertise more ac-curately and comprehensively than state-of-the-art systems that rely on the user’s bio or tweet content, (b) Cognos scales well due to built-in mechanisms to efficiently update its experts ’ database with new users, and (c) Despite relying only on a single feature, namely crowdsourced Lists, Cognos yields comparable, if not better, results in user tests, as com-pared to the official Twitter experts search engine for a wide range of queries. Our study highlights Lists as a potentially valuable source of information for future content or expert search systems in Twitter. 1.
lucent.com
"... lucent.com User interactions over social networks has been an emergent theme over the last several years. In contrast to previous work we focus on characterizing user communications pat-terns around an initial post, or conversation root. Specif-ically, we focus on how other users respond to these ro ..."
Abstract
- Add to MetaCart
(Show Context)
lucent.com User interactions over social networks has been an emergent theme over the last several years. In contrast to previous work we focus on characterizing user communications pat-terns around an initial post, or conversation root. Specif-ically, we focus on how other users respond to these roots and how the complete conversation initiated by this root evolves over time. For this purpose we focus our investi-gation on Twitter, the biggest micro-blogging social net-work. To the best of our knowledge this is the first such method that is able to reconstruct complete conversations around initial tweets. We propose a robust approach for reconstructing complete conversations and compare the re-sulting graph structures against those obtained from pre-vious crawling strategies based on keyword searches. Our crawl provides a large scale dataset, ideal for computer sci-entists to run large scale experimental evaluations, however our dataset is made of a collection of small scale, highly controlled and complete conversation graphs ideal for a so-ciological investigation. We believe our work will provide the proper dataset to establish concrete collaborations with interdisciplinary expertise.
Keywords: Query suggestion
, 2015
"... a b s t r a c t There are many web information management methods and techniques that help search engines and news services to provide useful suggestions with respect to queries, thus facilitating the users ’ search. However, the penetration of microblogging services in our daily life demands to als ..."
Abstract
- Add to MetaCart
(Show Context)
a b s t r a c t There are many web information management methods and techniques that help search engines and news services to provide useful suggestions with respect to queries, thus facilitating the users ’ search. However, the penetration of microblogging services in our daily life demands to also consider social sphere as far as query suggestion is concerned. Towards this direction, we introduce an algorithmic approach capable of creating a dynamic query suggestion set, which consist of the most viral and trendy Twitter Entities (that is hashtags, user mentions and URLs) with respect to a user's query. For evaluation purposes, we firstly compare the results derived from two case studies, against the suggestions of popular services like Google News, Yahoo! News, Bing News, and Reuters. In addition we further evaluate our approach with subjective user ratings against Google Trends service. Finally, we provide comparative results that clearly show that our proposal outperforms other methods and baselines in the respective literature. & 2015 Elsevier B.V. All rights reserved.
unknown title
"... Noname manuscript No. (will be inserted by the editor) Dynamic inference of social roles in information cascades ..."
Abstract
- Add to MetaCart
(Show Context)
Noname manuscript No. (will be inserted by the editor) Dynamic inference of social roles in information cascades
The Exponential Growth of Text Capture
, 2011
"... Approved for public release; distribution is unlimited. ..."
