Filters








10,358 Hits in 4.0 sec

Improving news ranking by community tweets

Xin Shuai, Xiaozhong Liu, Johan Bollen
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
Here, we propose a Community Tweets Voting Model (CTVM) to re-rank Google and Yahoo news search results on the basis of open, large-scale Twitter community data.  ...  Experimental results show that CTVM outperforms baseline rankings from Google and Yahoo for certain online communities.  ...  of the top k news documents using real-time tweets from the users' geo-location.  ... 
doi:10.1145/2187980.2188265 dblp:conf/www/ShuaiLB12 fatcat:tzj4vnasovcn3lzdgmenfmwmv4

Improving News Ranking by Community Tweets [article]

Xin Shuai and Xiaozhong Liu and Johan Bollen
2012 arXiv   pre-print
Here, we propose a Community Tweets Voting Model (CTVM) to re-rank Google and Yahoo news search results on the basis of open, large-scale Twitter community data.  ...  Experimental results show that CTVM outperforms baseline rankings from Google and Yahoo for certain online communities.  ...  of the top k news documents using real-time tweets from the users' geo-location.  ... 
arXiv:1202.3185v2 fatcat:bmj5c3n6srgpdivenovv2rptbi

The Impact of Future Term Statistics in Real-Time Tweet Search [chapter]

Yulu Wang, Jimmy Lin
2014 Lecture Notes in Computer Science  
In the real-time tweet search task operationalized in the TREC Microblog evaluations, a topic consists of a query Q and a time t, modeling the task where the user wishes to see the most recent but relevant  ...  To simulate the real-time aspect of the task in an evaluation setting, many systems search over the entire collection and then discard results that occur after the query time.  ...  The second author is grateful to Esther for her loving support and dedicates this work to Joshua and Jacob.  ... 
doi:10.1007/978-3-319-06028-6_58 fatcat:lcjpxmevjzamxaqv4iyykjhcja

Event based classification of Web 2.0 text streams [article]

Andreas Bauer, Christian Wolff
2013 arXiv   pre-print
We show the separative capabilities of event based features as the foundation for a real time search engine.  ...  To address this problem real time search engines have recently received increased attention.  ...  Real time search engines incorporate a micro corpus which is being update during and is only relevant for the time of the user search.  ... 
arXiv:1204.3362v2 fatcat:dp3nqrg7ebf6daw6sncmsbigqe

Learning to Rank Microblog Posts for Real-Time Ad-Hoc Search [chapter]

Jing Li, Zhongyu Wei, Hao Wei, Kangfei Zhao, Junwen Chen, Kam-Fai Wong
2015 Lecture Notes in Computer Science  
In this paper, we propose to utilize learning to rank model for microblog search.  ...  Extensive experimental studies demonstrate the effectiveness of learning to rank models and the usefulness to integrate microblog-specific and temporal information for microblog search task.  ...  In this paper, we extend a learning to rank framework for our real-time ad-hoc microblog search task.  ... 
doi:10.1007/978-3-319-25207-0_40 fatcat:nigfqigdjveztot4bujvpzhgqa

Finding top-k local users in geo-tagged social media data

Jinling Jiang, Hua Lu, Bin Yang, Bin Cui
2015 2015 IEEE 31st International Conference on Data Engineering  
In this work, we formulate a novel and useful problem called top-k local user search (TkLUS for short) from tweets with geo-tags.  ...  Furthermore, we devise two algorithms for processing TkLUS queries. Finally, we conduct an experimental study using real tweet data sets to evaluate the proposed techniques.  ...  ACKNOWLEDGMENTS The authors would like to thank Anders Skovsgaard for his generous help on collecting the geo-tagged tweet data used in the experimental study.  ... 
doi:10.1109/icde.2015.7113290 dblp:conf/icde/JiangL0C15 fatcat:ewroeyabpjcfvkpy5onqjkztti

Ranking Tweets Considering Trust and Relevance [article]

Srijith Ravikumar, Raju Balakrishnan, Subbarao Kambhampati
2012 arXiv   pre-print
We propose a method of ranking of tweets considering trustworthiness and content based popularity.  ...  The increasing popularity of Twitter and other microblogs makes improved trustworthiness and relevance assessment of microblogs evermore important.  ...  Recent trend of web search engines and online retailers considering the real-time trends in tweets for ranking products, news and recommendations aggravate this problem [5, 10] making microblog spamming  ... 
arXiv:1204.0156v1 fatcat:roexled6mzes3l3vobd7ehrp4m

Ranking tweets considering trust and relevance

Srijith Ravikumar, Raju Balakrishnan, Subbarao Kambhampati
2012 Proceedings of the Ninth International Workshop on Information Integration on the Web - IIWeb '12  
We propose a method of ranking of tweets considering trustworthiness and content based popularity.  ...  The increasing popularity of Twitter and other microblogs makes improved trustworthiness and relevance assessment of microblogs evermore important.  ...  Recent trend of web search engines and online retailers considering the real-time trends in tweets for ranking products, news and recommendations aggravate this problem [5, 10] making microblog spamming  ... 
doi:10.1145/2331801.2331805 fatcat:y6qh2ltocvc7tpw2k6xmpzjp3m

On real-time ad-hoc retrieval evaluation

Stephen E. Robertson, Evangelos Kanoulas
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
In a real-time search task however users not only wish to retrieve the most relevant items but the most recent as well.  ...  In this poster, we redefine the experiment for a real-time ad-hoc search task, by setting new submission requirements for the submitted systems/runs, proposing metrics to be used in evaluating the submissions  ...  Evaluating a system over a real-time ad-hoc task clearly requires a measure that accounts both for relevance and recency.  ... 
doi:10.1145/2348283.2348498 dblp:conf/sigir/RobertsonK12a fatcat:spq5efactng27my4dczsl3u5hm

News vertical search using user-generated content

Richard McCreadie
2012 SIGIR Forum  
content for real-time news search.  ...  The aim of this task was to find the most relevant tweets for the user query in a real-time setting, i.e. to retrieve tweets on or before a point in time.  ...  The average Web search query is between 2-3 terms in length (Bar-Ilan et al., 2009) , however, news queries may be longer than this if the user is searching for a specific story, e.g.  ... 
doi:10.1145/2492189.2492202 fatcat:wuha3gotmnffnbqhrdltooys5m

Exploiting ranking factorization machines for microblog retrieval

Runwei Qiang, Feng Liang, Jianwu Yang
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Furthermore, it outperforms the best performing results in the TREC'12 Real-Time Search Task.  ...  Learning to rank method has been proposed for practical application in the field of information retrieval.  ...  The evaluation measures are P@30 and MAP with respect to highrel (i.e. tweet set judged as highly relevant) and P@30 is the official main metric for the real-time search task in 2011 and 2012.  ... 
doi:10.1145/2505515.2505648 dblp:conf/cikm/QiangLY13 fatcat:r7x4hqvrabgcjfxlzwee55luhe

Dynamic Model for Query-Document Expansion towards Improving Retrieval Relevance [article]

Onifade Olufade, Arise Abiola, Ogboo Chisom
2021 arXiv   pre-print
This research work focuses on two methods of retrieval for both tweet-length queries and sentence-length queries.  ...  Getting relevant information from search engines has been the heart of research works in information retrieval.  ...  TWEET RETRIEVAL Bernard [13] suggested that the problem with real-time search is defining an effective ranking function.  ... 
arXiv:2103.10474v1 fatcat:gd2hkm6o5fgwhiaghezivtw7qy

Twitter message recommendation based on user interest profiles

Raheleh Makki, Axel J. Soto, Stephen Brooks, Evangelos E. Milios
2016 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)  
We aim to tackle this problem by integrating active learning techniques into tweet recommendation, more specifically for finding relevant tweets and ranking them.  ...  Twitter users gather information about their topics of interest through their followees' posts or by searching for relevant posts.  ...  We consider the language model-based retrieval using Dirichlet smoothing [13] as our baseline relevance model. This model retrieves a list of tweets ranked by their relevance to the search query.  ... 
doi:10.1109/asonam.2016.7752266 dblp:conf/asunam/MakkiSBM16 fatcat:3jrug3ieu5ab3byukap3phurum

Exploiting real-time information retrieval in the microblogosphere

Feng Liang, Runwei Qiang, Jianwu Yang
2012 Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries - JCDL '12  
Specifically, the proposed system gives 26.37% and 9.94% further increases in P@30 and MAP over the best performing result on highrel in the TREC'11 Real-Time Search Task.  ...  For the temporal re-ranking, we suggest several methods to evaluate the temporal aspects of documents.  ...  The real-time search task can be summarized as "At time t, find tweets about topic X".  ... 
doi:10.1145/2232817.2232867 dblp:conf/jcdl/LiangQY12 fatcat:gl4oyuuyffbijhubd7753l4nzi

News vertical search

Richard McCreadie, Craig Macdonald, Iadh Ounis
2013 Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '13  
For these queries, we have crowdsourced workers compare Web search rankings for each, with similar rankings integrating real-time news content from sources such as Twitter or the blogosphere.  ...  We sampled approximately 300 news-related search queries using Google Trends and Bitly data in real-time for two time periods.  ...  to return for such real-time news-related information needs.  ... 
doi:10.1145/2484028.2484080 dblp:conf/sigir/McCreadieMO13 fatcat:vnygrtoaovhkle24vu4iziwe4q
« Previous Showing results 1 — 15 out of 10,358 results