Filters








863 Hits in 6.8 sec

An event extraction model based on timeline and user analysis in Latent Dirichlet allocation

Bayar Tsolmon, Kyung-Soon Lee
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
The Latent Dirichlet Allocation (LDA) topic model is adapted with the weights of event terms on timeline and reliable users to extract social events.  ...  This paper proposes an event extraction method which combines user reliability and timeline analysis.  ...  This paper proposes an event extraction model, which is a Latent Dirichlet Allocation topic model based on timeline and user behavior analysis.  ... 
doi:10.1145/2600428.2609541 dblp:conf/sigir/TsolmonL14 fatcat:5azgsjqi4bgwdcxgbtwvh3ac7q

Event-based text visual analytics

Ji Wang, Lauren Bradel, Chris North
2014 2014 IEEE Conference on Visual Analytics Science and Technology (VAST)  
In addition to applying entity extraction and topic modeling, we enable the user to explore a large dataset using multi-model semantic interaction, which infers analytical reasoning from user actions to  ...  We present an event-based approach for solving a directed sensemaking task in which we combine powerful information foraging tools with intuitive synthesis spaces to solve the VAST 2014 Mini-Challenge  ...  ACKNOWLEDGMENTS This work was supported in part by NSF grants IIS-1218346 and SES-1111239.  ... 
doi:10.1109/vast.2014.7042552 dblp:conf/ieeevast/WangBN14 fatcat:j3gfrdojyvbt7pqudg5bmo5nay

Visualization of Clandestine Labs from Seizure Reports: Thematic Mapping and Data Mining Research Directions [article]

William Hsu, Mohammed Abduljabbar, Ryuichi Osuga, Max Lu, Wesam Elshamy
2015 arXiv   pre-print
We present an approach to event extraction that is driven by data mining and visualization goals, particularly thematic mapping and trend analysis.  ...  The problem of spatiotemporal event visualization based on reports entails subtasks ranging from named entity recognition to relationship extraction and mapping of events.  ...  Figure 3 . 3 Plate model for Latent Dirichlet Allocation (LDA) in a system with an N-word lexicon, D documents, and K topics.  ... 
arXiv:1503.01549v1 fatcat:5usymj3c6zhn7jsf426s2mic6a

Analysis of Topic Modeling with Unpooled and Pooled Tweets and Exploration of Trends during Covid

Jaishree Ranganathan, Tsega Tsahai
2021 International Journal of Computer Science Engineering and Applications  
Topic modeling is an unsupervised algorithm to discover a hidden pattern in text documents. In this study, we explore the Latent Dirichlet Allocation (LDA) topic model algorithm.  ...  Social media analytics helps make informed decisions based on people's needs and opinions.  ...  Focus on analyzing the topics and themes during this period on Twitter using Latent Dirichlet Allocation (LDA) topic modeling approach.  ... 
doi:10.5121/ijcsea.2021.11601 fatcat:skusdyt5uneifpobgsehvrurai

RescueMark: Visual Analytics of Social Media Data for Guiding Emergency Response in Disaster Situations: Award for Skillful Integration of Language Model

Astrik Jeitler, Alpin Turkoglu, Denis Makarov, Timo Jockers, Juri Buchmuller, Udo Schlegel, Daniel A. Keim
2019 2019 IEEE Conference on Visual Analytics Science and Technology (VAST)  
We describe the data analysis and visualization process of the social media data applied to extract the relevant information.  ...  RescueMark provides spatial, topic and temporal event exploration supporting decision making for resource allocation and determine damaged areas of the city.  ...  For this, we applied the Latent Dirichlet Allocation (LDA) algorithm [1] to extract topic terms for each messages.  ... 
doi:10.1109/vast47406.2019.8986898 dblp:conf/ieeevast/JeitlerTMJBSK19 fatcat:xtkldccevvbathh4hh42kfjme4

User Group Oriented Temporal Dynamics Exploration

Zhiting Hu, Junjie Yao, Bin Cui
2014 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This paper proposes GrosToT (Group Specific Topics-over-Time), a unified probabilistic model to infer latent user groups and temporal topics at the same time.  ...  Specifically, groups' attention to their medium-interested topics are event-driven, showing rich bursts; while its engagement in group's dominating topics are interest-driven, remaining stable over time  ...  Acknowledgments This research is supported by the National Natural Science Foundation of China under Grant No. 61272155, and 973 program under No. 2014CB340405.  ... 
doi:10.1609/aaai.v28i1.8723 fatcat:qrnkx7sqqnemfnwdcpxyutwriy

Hashtags are (not) judgemental: The untold story of Lok Sabha elections 2019 [article]

Saurabh Gupta, Asmit Kumar Singh, Arun Balaji Buduru, Ponnurangam Kumaraguru
2020 arXiv   pre-print
Second, we use Latent Dirichlet Allocation to find topic patterns in the dataset. In the end, we use skip-gram word embedding model to find semantically similar hashtags.  ...  We study the trends and events unfolded on the ground, the latent topics to uncover representative hashtags and semantic similarity to relate hashtags with the election outcomes.  ...  We used Latent Dirichlet Allocation (LDA) to find latent topics among the hashtags in an unsupervised manner.  ... 
arXiv:1909.07151v2 fatcat:ahisl3a2rzcivbm2v7lurpaite

Time and information retrieval: Introduction to the special issue

Leon Derczynski, Jannik Strötgen, Ricardo Campos, Omar Alonso
2015 Information Processing & Management  
using Latent Dirichlet Allocation Model" (Kar, Nunes, & Ribeiro, 2015) .  ...  Evaluation over a set of Wikipedia articles shows that a method based on Latent Dirichlet Allocation achieved strong above-baseline performance.  ... 
doi:10.1016/j.ipm.2015.05.002 fatcat:rgh7qcsn3zfztb637r3zcqsjkm

A Low-Rank Approximation Approach to Learning Joint Embeddings of News Stories and Images for Timeline Summarization

William Yang Wang, Yashar Mehdad, Dragomir R. Radev, Amanda Stent
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
Previous studies in extractive timeline generation are limited in two ways: first, most prior work focuses on fully-observable ranking models or clustering models with hand-designed features that may not  ...  In experiments, we compare our model to various competitive baselines, and demonstrate the stateof-the-art performance of the proposed textbased and multimodal approaches.  ...  Acknowledgments The authors would like to thank Kapil Thadani and the anonymous reviewers for their thoughtful comments.  ... 
doi:10.18653/v1/n16-1008 dblp:conf/naacl/WangMRS16 fatcat:iv2x23umuralnbt7oask3xs2yy

Building a semantic recommendation engine for news feeds based on emerging topics from tweets

Mihai Tabara, Mihai Dascalu, Stefan Trausan-Matu
2016 2016 15th RoEduNet Conference: Networking in Education and Research  
In this paper, we approach the problem of topic extraction from Twitter in the context of designing a recommendation engine to best matching user profiles to news feed articles.  ...  Alongside its advent, textual analysis changed as new user-centered content failed to comply with traditional grammar ruling.  ...  Acknowledgment The work presented in this paper was partially funded by the EC H2020 project RAGE (Realising and Applied Gaming Eco-System) http://www.rageproject.eu/ Grant agreement No 644187.  ... 
doi:10.1109/roedunet.2016.7753209 fatcat:fywcfbdd3bdkznzhsvdiyxih3y

Social-media insights into US mental health amid the COVID-19 global pandemic: a Longitudinal analysis of publicly available Twitter data (January 22- April 10, 2020) (Preprint)

Danny Valdez, Marijn ten Thij, Krishna Bathina, Lauren Alexandra Rutter, Johan Bollen
2020 Journal of Medical Internet Research  
First, we characterized the evolution of hashtags over time using Latent Dirichlet Allocation (LDA) topic modeling.  ...  Finally, VADER sentiment analysis sentiment scores of user timelines were initially high and stable, but decreased significantly, and continuously, by late March.  ...  Latent Dirichlet Allocation Topic Models Latent Dirichlet allocation (LDA) topic models are unsupervised machine learning tools that perform probabilistic inferences to consolidate large volumes of text  ... 
doi:10.2196/21418 pmid:33284783 fatcat:ryq3uhkmqbazlbp5nqhdctwlga

A Semantic Aspect-Based Vector Space Model to Identify the Event Evolution Relationship within Topics

Yaoyi Xi, Bicheng Li, Yang Liu
2015 Journal of Computing Science and Engineering  
A topic usually consists of multiple related events, and the accurate identification of event evolution relationship plays an important role in topic evolution analysis.  ...  Then, construct a semantic aspect-based vector space model according to these aspects. Finally, represent each event as a point and measure the semantic relatedness between events in the space.  ...  In addition, the topic model can be less affected by synonymy and polysemy. Latent Dirichlet allocation (LDA) [11] is a typical topic model.  ... 
doi:10.5626/jcse.2015.9.2.73 fatcat:nv3tednaxvbqhc5mb5qitqezni

Discovering Latent Patterns of Urban Cultural Interactions in WeChat for Modern City Planning

Xiao Zhou, Anastasios Noulas, Cecilia Mascolo, Zhongxiang Zhao
2018 Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18  
We exploit rich spatio-temporal representations on user activity at cultural venues and use a novel extended version of the traditional latent Dirichlet allocation model that incorporates temporal information  ...  To this end, the optimal allocation of cultural establishments and related resources across urban regions becomes of vital importance, as it can reduce financial costs in terms of planning and improve  ...  We would also like to thank Bo Chen and Huanzhong Duan in the WeChat group for their valuable comments and helpful suggestions.  ... 
doi:10.1145/3219819.3219929 dblp:conf/kdd/ZhouNMZ18 fatcat:dicu37s4znbifbyumxat6ilgsa

Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition

Junghoon Chae, Dennis Thom, Harald Bosch, Yun Jang, Ross Maciejewski, David S. Ebert, Thomas Ertl
2012 2012 IEEE Conference on Visual Analytics Science and Technology (VAST)  
In order to find and understand abnormal events, the analyst can first extract major topics from a set of se- lected messages and rank them probabilistically using Latent Dirichlet Allocation.  ...  In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance.  ...  Department of Homeland Securitys VACCINE Center under Award Number 2009-ST-061-CI0003, the German Federal Ministry for Education and Research (BMBF) as part of the VASA project, and the European Commission  ... 
doi:10.1109/vast.2012.6400557 dblp:conf/ieeevast/ChaeTBJMEE12 fatcat:gevduox26fdddipfh5go3dqexa

Context-aware social media user sentiment analysis

Bo Liu, Shijiao Tang, Xiangguo Sun, Qiaoyun Chen, Jiuxin Cao, Junzhou Luo, Shanshan Zhao
2020 Tsinghua Science and Technology  
In this study, we propose a novel model for performing context-aware user sentiment analysis.  ...  Based on our experimental results obtained using the Twitter dataset, our approach is observed to outperform the other existing methods in analysing user sentiment.  ...  Fig. 8 8 Performance comparison based on the contributions of comments and users' timelines.  ... 
doi:10.26599/tst.2019.9010021 fatcat:ib6ezkm4onbu5cuqcgqwflml4a
« Previous Showing results 1 — 15 out of 863 results