Filters








8,989 Hits in 2.3 sec

TREC 2012 Microblog Track Experiments at Kobe University

Taiki Miyanishi, Kazuhiro Seki, Kuniaki Uehara
2012 Text Retrieval Conference  
The approach uses twostage relevance feedback to model search interests and temporal dynamics on a microblog. The first relevance feedback uses a single user-selected tweet as feedback.  ...  We also use this temporal property to select topic-related terms that have similar temporal dynamics to an original query.  ...  The next step re-retrieves tweets with the new query using time-based query expansion method, which leverages temporal variation of a given topic and its topic-related terms.  ... 
dblp:conf/trec/MiyanishiSU12 fatcat:lyrbmbqy3rbuhlrywytjn7qkni

Identifying Covid-19 misinformation tweets and learning their spatio-temporal topic dynamics using Nonnegative Coupled Matrix Tensor Factorization

Thirunavukarasu Balasubramaniam, Richi Nayak, Khanh Luong, Md. Abul Bashar
2021 Social Network Analysis and Mining  
Firstly, a novel ranking-based approach leveraging the scalable information retrieval infrastructure is applied to detect misinformation from a huge collection of unlabelled tweets based on a related but  ...  Secondly, the identified misinformation tweets are represented as a coupled matrix tensor model and Nonnegative Coupled Matrix Tensor Factorization is applied to learn their spatio-temporal topic dynamics  ...  related tweets.  ... 
doi:10.1007/s13278-021-00767-7 pmid:34149960 pmcid:PMC8204930 fatcat:yahzuip34vb2rhieny3pj3w3zy

Topic Evolution Analysis in Social Networking Services: Taking Sina Weibo as an Example

Yuhui Wang
2018 Computer systems science and engineering  
We collect text data from sina Weibo and vectorize each tweets, before using a dynamic topic model to discover the event-related topics.  ...  The keyword corresponds to a global ransomware attack in May 2017, on which our example event-related topics are based.  ...  Furthermore, we use dynamic topic model with 5 topics to discover the topic of each tweets.  ... 
doi:10.32604/csse.2018.33.287 fatcat:nsxwnpqjsnce3dpptj2r2rw3ye

Real World City Event Extraction from Twitter Data Streams

Yuchao Zhou, Suparna De, Klaus Moessner
2016 Procedia Computer Science  
We apply our developed approach to a real world dataset of tweets collected from the city of London.  ...  We also develop a named entity recognition model to obtain the precise location of the related events and provide a qualitative estimation of the impact of the detected events.  ...  The approach consists of the following steps: Tweet retrieval The tweets are retrieved from the Twitter search website API (https://twitter.com/search-home).  ... 
doi:10.1016/j.procs.2016.09.069 fatcat:kiha4ppferefpmfj6ubxyjafqu

UWM-HBUT at TREC 2014 Microblog Track: Using Query Expansion (QE) and Event Identification Algorithm (EIA) to improve microblog retrieval effectiveness

Sukjin You, Xiangming Mu, Wei Huang
2014 Text Retrieval Conference  
The ranking score of a retrieved tweet is adjusted by considering how close the tweet time stamp is to the event using Event Identification Algorithm (EIA).  ...  Considering sensitivity to time, we introduce a new factor to help to improve tweet retrieval effectiveness.  ...  According to the author, this approach could capture the dynamic and entity-oriented topics in microblogs.  ... 
dblp:conf/trec/YouMH14 fatcat:j77owohlgncfthi66qfdqk6kru

Twitter News Credibility Meter

Zareen Sharf, Anwar Us Saeed
2013 International Journal of Computer Applications  
The application will be dynamically retrieving tweets and storing them in the database and the assessment bar and tag cloud will also change dynamically every time a new dataset is retrieved.  ...  [1] discovered that 85% of discussion topics on twitter are related to news.  ... 
doi:10.5120/14456-2729 fatcat:ygya3g4pz5dexowrfofr5ode4a

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  
Based on the timeline relevance model, the duration of the related event was defined as an exploring period to retrieve the topic-related tweets, and an event summarizing algorithm was designed to further  ...  First, the initial hashtag was used to retrieve the relevant tweets. Further, the TF-IDF value of each word in the related tweet set was calculated.  ... 
doi:10.1007/s11432-016-9333-4 fatcat:5w7eef6ydzhopkhfasrmjlwioa

Multidimensional Relevance in Microblog Search

Divi Galih Prasetyo Putri
2019 BCS-IRSG Symposium on Future Directions in Information Access  
In Information Retrieval, the assessment of relevance is affected by multiple criteria.  ...  We can see in Fig. 1 that adding informativeness value can improve the performance of disaster-related tweet retrieval.  ...  Microblog search. 1 . 1 Disaster Related Retrieval: SMERP 2017 on Text Retrieval (Task 1) 1 2.  ... 
dblp:conf/fdia/Putri19 fatcat:4uk4fajh7jfqvk55hoebp6umlm

Fast NLP-based Pattern Matching in Real Time Tweet Recommendation

Zheng Gao, John Wolohan
2017 Text Retrieval Conference  
This year, TREC (Text REtrieval Conference) offers a Real Time Summarization track to explore online user reading preference on Twitter, one of the largest social media platform so far, to figure out recommendation  ...  As both tweets and topics are unstructured text information, in order to extract quantitative information out of them, NLP related methods are applied.  ...  Afterwards it applies a Time-adjusted Dynamic Thresholdbased model to generate recommendations for given topics. [10] leverages an idf -based term weighting scheme as well as Jaccard similarity method  ... 
dblp:conf/trec/GaoW17 fatcat:ixs7ixyehjel3h7klkxwz44qji

Using Event Identification Algorithm (EIA) to Improve Microblog Retrieval Effectiveness

Sukjin You, Wei Huang, Xiangming Mu
2015 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)  
The ranking score of a retrieved tweet is adjusted by considering how close the tweet time stamp is to the event using Event Identification Algorithm (EIA).  ...  Considering sensitivity to time, we introduce a new factor to help to improve tweet retrieval effectiveness.  ...  According to the author, this approach could capture the dynamic and entity-oriented topics in microblogs.  ... 
doi:10.1109/wi-iat.2015.215 dblp:conf/webi/YouHM15 fatcat:uy2anhvlvbcihkjvkxhzyblngy

Active Keyword Selection to Track Evolving Topics on Twitter [article]

Sacha Lévy, Farimah Poursafaei, Kellin Pelrine, Reihaneh Rabbany
2022 arXiv   pre-print
Our experiments show that our method achieves an average topic-related keyword recall 2x higher than baselines.  ...  We leverage a large open-source COVID-19 Twitter dataset to illustrate the applicability of our method in tracking Tweets around the key sub-topics of Vaccine, Mask, and Lockdown.  ...  We do not sample the oracle keywords for the topic of Vaccine as they are already a few keywords and tweets related to the topic.  ... 
arXiv:2209.11135v1 fatcat:43zp6kw7hvhh7hsep4wdh5nzju

Exploiting Twitter for Border Security-Related Intelligence Gathering

Jakub Piskorski, Hristo Tanev, Alexandra Balahur
2013 2013 European Intelligence and Security Informatics Conference  
labeling: h-positive h-positive multiexclamation austria will negator be the same rt user visa positive positive h-positive 22 days to europe topic topic Event-related Tweet Retrieval submit several  ...  information on crisis-related events in third countries automatically extracted from online news with information extracted from Twitter Retrieving tweets with opinions and information related to migration  ... 
doi:10.1109/eisic.2013.63 dblp:conf/eisic/PiskorskiTB13 fatcat:tw44tnc7xffaddoqqalr4ygvj4

Proactive Query Expansion for Streaming Data Using External Source [article]

Farah Alshanik, Amy Apon, Yuheng Du, Alexander Herzog, Ilya Safro
2022 arXiv   pre-print
We employ Dynamic Eigenvector Centrality to trigger the emergent events, and the Latent Dirichlet Allocation to discover the topics.  ...  The quality of the retrieved results was measured using a quality indicator of the streaming data: tweets count, hashtag count, and hashtag clustering.  ...  Information retrieval systems typically use query expansion techniques to enhance the initial user query, e.g., by adding inflected forms, cognates, and related words manually retrieved from the text.  ... 
arXiv:2201.06592v1 fatcat:jjbxche7w5hu3akey2ooud4xwy

University of Waterloo at TREC 2015 Microblog Track

Luchen Tan, Adam Roegiest, Charles L. A. Clarke
2015 Text Retrieval Conference  
The top 1000 tweets were retrieved from Twitter commercial search engine by applying the title of the topic as a query.  ...  Given a topic with title, narrative and description, we start by building a language model for the topic.  ...  Thus, in addition to the normal retrieval processes, the choice of pushing strategy is also significant. However, Scenario B is more like a retrieval task based on a one-day tweet collection.  ... 
dblp:conf/trec/TanRC15 fatcat:axeapi46z5ffbccmwn2ctgfwhq

Dynamic theme tracking in Twitter

Liang Zhao, Feng Chen, Chang-Tien Lu, Naren Ramakrishnan
2015 2015 IEEE International Conference on Big Data (Big Data)  
In this paper, we propose a dynamic query expansion (DQE) model for theme tracking in Twitter.  ...  It is socially significant to surveil the tweet content under crucial themes such as "disease" and "civil unrest".  ...  Though the theme query represents the generic concept of a theme, the retrieved theme-related content can dynamically evolve when different theme-related occurrences become popular in Twitter.  ... 
doi:10.1109/bigdata.2015.7363800 dblp:conf/bigdataconf/ZhaoCLR15 fatcat:jut5gekwzjbmteoahbhlesycza
« Previous Showing results 1 — 15 out of 8,989 results