Filters








1,043 Hits in 4.9 sec

Improving pseudo-relevance feedback via tweet selection

Taiki Miyanishi, Kazuhiro Seki, Kuniaki Uehara
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
To overcome the limitation of pseudo-relevance feedback for microblog search, we propose a novel query expansion method based on two-stage relevance feedback that models search interests by manual tweet  ...  Pseudo-relevance feedback assumes that the top ranked documents in the initial search results are relevant and that they contain topic-related words appropriate for relevance feedback.  ...  Those results suggest that the top ranked 30 tweets tend to contain a relevant tweet that can improve the retrieval performance via TSF, so that microblog users should read the top 30 tweets and select  ... 
doi:10.1145/2505515.2505701 dblp:conf/cikm/MiyanishiSU13 fatcat:ynype27wp5h5lmpv2pur5p7bs4

Query Expansion Based on a Feedback Concept Model for Microblog Retrieval

Yashen Wang, Heyan Huang, Chong Feng
2017 Proceedings of the 26th International Conference on World Wide Web - WWW '17  
We tackle the problem of improving microblog retrieval algorithms by proposing a Feedback Concept Model for query expansion.  ...  In the proposed feedback concept model: (i) we mine the concept information implicit in short-texts based on the external knowledge bases; (ii) with the relevant concepts associated with short-texts, a  ...  As the 1st stage in the pseudo-relevance feedback strategy, we should construct the Pseudo-Relevance Documents, which is called the Concept-Relevant Feedback Tweets (denoted as CT ) in this paper.  ... 
doi:10.1145/3038912.3052710 dblp:conf/www/WangHF17 fatcat:5ect7jzwjnfq7jfl7nzk6gj2sy

Temporal feedback for tweet search with non-parametric density estimation

Miles Efron, Jimmy Lin, Jiyin He, Arjen de Vries
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
Temporal feedback improves over standard lexical feedback (with and without human judgments), illustrating that temporal relevance signals exist independently of document content.  ...  We explore this question in the context of tweet search and temporal feedback: starting with an initial set of results from a baseline retrieval model, we estimate the temporal density of relevant documents  ...  From the top k reranked documents, estimate feedback models: in the pseudo-relevance feedback case, this involves selecting the top k documents and assuming that they are relevant. 3 Training γ led to  ... 
doi:10.1145/2600428.2609575 dblp:conf/sigir/EfronLHV14 fatcat:7keb47pfyrcozfaex47te42hae

Hyperlink-extended pseudo relevance feedback for improved microblog retrieval

Tarek El-Ganainy, Walid Magdy, Ahmed Rafea
2014 Proceedings of the first international workshop on Social media retrieval and analysis - SoMeRA '14  
In this paper we comprehensively investigate query expansion for microblog retrieval using pseudo relevance feedback (PRF) with different configurations.  ...  Results also showed that utilizing hyperlinked documents in tweets for query expansion improves results over traditional PRF.  ...  Most of the reported works on query expansion mainly applied pseudo relevance feedback (PRF) by assuming top retrieved documents relevant and selecting a set of terms to be added to the query for a second  ... 
doi:10.1145/2632188.2632204 dblp:conf/sigir/El-GanainyMR14 fatcat:z4rjnrmorzgprdnak6impvugfa

Generating event storylines from microblogs

Chen Lin, Chun Lin, Jingxuan Li, Dingding Wang, Yang Chen, Tao Li
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
We first propose a language model with dynamic pseudo relevance feedback to obtain relevant tweets, and then generate storylines via graph optimization.  ...  Top 30 documents retrieved by RLM on the original query are selected as pseudo relevance feedback; (9) LP: Dynamic pseudo relevance feedback (DPRF) with local power distribution, with n = 5 burst periods  ...  Language model based query expansion via dynamic pseudo relevance feedback is described in Section 4. Section 5 presents the framework for storyline generation.  ... 
doi:10.1145/2396761.2396787 dblp:conf/cikm/LinLLWCL12 fatcat:7w2rmpvdpbgevfe27um7i25yyu

Exploiting Geolocation, User and Temporal Information for Natural Hazards Monitoring in Twitter

Víctor Fresno, Arkaitz Zubiaga, Heng Ji, Raquel Martínez-Unanue
2015 Revista de Procesamiento de Lenguaje Natural (SEPLN)  
Considerar información de geolocalización, usuario o temporal dentro de un enfoque de pseudo-relevance feedback, nos permite encontrar terminología relacionada con el evento, pero no coocurrente con las  ...  Pseudo-Relevance Feedback (PRF) via query expansion (Xu and Croft, 1996) has been proven to be effective in many Information Retrieval (IR) tasks.  ...  The approaches we introduce and experiment in this paper rely on geolocation, user and hashtag information, as well as temporal information in a Pseudo-Relevance Feedback via query expansion approach.  ... 
dblp:journals/pdln/FresnoZJM15 fatcat:6nittielyvdw7ehefoygbb5sue

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  
For the query modeling, we introduce a two-stage pseudo-relevance feedback query expansion to overcome the severe vocabulary-mismatch problem of short message retrieval in microblog.  ...  Experimental results demonstrate that our approach obtains significant improvements compared with baseline systems.  ...  than the earliest one to generate the feedback words; however, selecting the tweet according to the highest relevance score as the single support tweet can improve the system performance significantly  ... 
doi:10.1145/2232817.2232867 dblp:conf/jcdl/LiangQY12 fatcat:gl4oyuuyffbijhubd7753l4nzi

Modeling Temporal Evidence from External Collections

Flávio Martins, João Magalhães, Jamie Callan
2019 Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining - WSDM '19  
In particular, we show that temporal evidence of external collections can be used to (i) infer a topic's temporal relevance, (ii) select the query expansion terms, and (iii) re-rank the final results for  ...  Recent advances have shown how to improve the estimation of the temporal relevance of such topics. In this approach, we build on two major novelties.  ...  In the pseudo-relevance feedback term selection stage it is used to generate temporally focused query expansion terms.  ... 
doi:10.1145/3289600.3290966 dblp:conf/wsdm/MartinsMC19 fatcat:mufci7jcyvcnjnwvjrknrivabe

Reproducible Experiments on Lexical and Temporal Feedback for Tweet Search [chapter]

Jinfeng Rao, Jimmy Lin, Miles Efron
2015 Lecture Notes in Computer Science  
In this paper, we illustrate both advantages by providing open-source implementations of lexical and temporal feedback techniques for tweet search built on the TREC Microblog API.  ...  Following common parameter settings, we estimated the relevance models from k = 50 pseudo-relevant documents and selected n = 20 feedback terms.  ...  Since tweets are very short, a number of researchers have suggested that the query expansion effects of pseudo-relevance feedback are beneficial to search effectiveness.  ... 
doi:10.1007/978-3-319-16354-3_82 fatcat:d2mecxikwrdqxjlj5bteu75ocm

Simple Dynamic Emission Strategies for Microblog Filtering

Luchen Tan, Adam Roegiest, Charles L.A. Clarke, Jimmy Lin
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
We explore and evaluate multiple threshold setting strategies, including purely static thresholds, dynamic thresholds without user feedback, and dynamic thresholds with daily feedback.  ...  Our best technique takes advantage of daily feedback in a simple yet effective manner, achieving the best known result reported in the literature to date.  ...  Since relevant tweets may not contain all, or even any, of the title terms, we employed a pseudo-relevance feedback step to expand the title terms with 5 hashtags and 10 other terms.  ... 
doi:10.1145/2911451.2914704 dblp:conf/sigir/TanRCL16 fatcat:cikhe2o56jaq7bcwg5v7ld3uky

Local versus Global Strategies in Social Query Expansion [article]

Omar Alonso, Vasileios Kandylas, Serge-Eric Tremblay
2019 arXiv   pre-print
Related to our work, a two-step extension for computing pseudo-relevance feedback that contains a manual tweet selection and query-document temporal relevance model is described in [3] . ere are similarities  ...  Similar to pseudo relevance feedback, ranking documents extracted from tweets by our voting system indicate that the top-k links are relevant to a given query (i.e., hashtag) on a speci c time period,  ... 
arXiv:1908.01868v1 fatcat:zpq7ekovcbcbrfndrt5ustbygu

News comments generation via mining microblogs

Xuezhi Cao, Kailong Chen, Rui Long, Guoqing Zheng, Yong Yu
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
In this paper, we present a framework to automatically collect relevant microblogs from microblogging websites to generate comments for popular news on news websites.  ...  That is why relevance feedback gets more improvement on the political category because tweets about politics are often written officially and formally.  ...  For pseudo relevance feedback, the size of the keyword set after feedback is 1.3 time as large as the origin.  ... 
doi:10.1145/2187980.2188082 dblp:conf/www/CaoCLZY12 fatcat:n2mr2yivaffgvhikezjodpofba

An event summarizing algorithm based on the timeline relevance model in Sina Weibo

Kai Lei, Lizhu Zhang, Ying Liu, Ying Shen, Chenwei Liu, Qian Yu, Weitao Weng
2018 Science China Information Sciences  
An event summarizing algorithm based on the timeline relevance model in Sina Weibo. Sci China Inf Sci, 2018, 61(12): 129101, https://doi.  ...  To enhance the expression of the query and to associate more relevant tweets, a hashtag expanding language model with dynamic pseudo relevance feedback was proposed.  ...  W ti 2 represents the term weight that calculated using the pseudo relevance feedback method [7]. First, the initial hashtag was used to retrieve the relevant tweets.  ... 
doi:10.1007/s11432-016-9333-4 fatcat:5w7eef6ydzhopkhfasrmjlwioa

Query Expansion for Microblog Retrieval Focusing on an Ensemble of Features

Abu Nowshed Chy, Md Zia Ullah, Masaki Aono
2019 Journal of Information Processing  
Upon retrieving tweets by our proposed topic modeling based query expansion, we utilize the pseudo-relevance feedback and a new temporal relatedness approach to select the candidate tweets.  ...  Next, we devise several new features to select the temporally and semantically relevant expansion terms by leveraging the temporal, word embedding, and sentiment association of candidate term and query  ...  Most of these methods are based on the pseudo-relevance feedback (PRF) and select the terms from the top retrieved tweets as PRF assumes the top retrieved tweets are relevant.  ... 
doi:10.2197/ipsjjip.27.61 fatcat:n3q4l6tmn5fh7ppdjvqpbcmjt4

Feature Analysis in Microblog Retrieval Based on Learning to Rank [chapter]

Zhongyuan Han, Xuwei Li, Muyun Yang, Haoliang Qi, Sheng Li
2013 Communications in Computer and Information Science  
The experimental results on the TREC microblog collection show that textual features, i.e. content relevance between a query and a microblog, contribute most to the retrieval performance.  ...  To address this issue, this paper examines the contribution of each single feature together with the contribution of the feature combinations via the ranking SVM for microblog retrieval modeling.  ...  , author and tweet unique, are examined via Ranking SVM.  ... 
doi:10.1007/978-3-642-41644-6_40 fatcat:ymbtwftzavhsbm4rebwtyaupai
« Previous Showing results 1 — 15 out of 1,043 results