Filters








6,691 Hits in 4.0 sec

The generalized dirichlet distribution in enhanced topic detection

Karla L. Caballero, Joel Barajas, Ram Akella
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
We model the prior distribution of topics by a Generalized Dirichlet distribution (GD) rather than a Dirichlet distribution as in Latent Dirichlet Allocation (LDA). We define this model as GD-LDA.  ...  As a tree model, it accommodates the most important set of topics in the upper part of the tree based on their probability mass.  ...  THE GENERALIZED DIRICHLET DIS-TRIBUTION Properties and Intuition The Generalized Dirichlet (GD) distribution was introduced by Connor and Mosimann in [4] .  ... 
doi:10.1145/2396761.2396860 dblp:conf/cikm/CaballeroBA12 fatcat:hrvq2xhuybbwfcskotwzjcnzoa

MEI: Mutual Enhanced Infinite Generative Model for Simultaneous Community and Topic Detection [chapter]

Dongsheng Duan, Yuhua Li, Ruixuan Li, Zhengding Lu, Aiming Wen
2011 Lecture Notes in Computer Science  
To detect the appropriate number of communities and topics automatically, Hierarchical/Dirichlet Process Mixture model (H/DPM) is employed.  ...  To discover community, topic and their relations simultaneously, a mutual enhanced infinite generative model (MEI) is proposed.  ...  Mutual Enhanced Generative Model The graphical representation of the finite version of the proposed model, i.e. mutual enhanced generative model (ME), is shown in Figure 1 .  ... 
doi:10.1007/978-3-642-24477-3_10 fatcat:qxuc5ahd2bcntkrm4hzd5rd4ei

MEI: Mutual Enhanced Infinite Community-Topic Model for Analyzing Text-Augmented Social Networks

D. Duan, Y. Li, R. Li, Z. Lu, A. Wen
2012 Computer journal  
We propose a mutual enhanced infinite community-topic model (MEI) to detect communities and topics simultaneously in text-augmented social networks.  ...  Experiments on the co-author network built from a subset of DBLP data show MEI outperforms the baseline models in terms of generalization performance.  ...  ACKNOWLEDGEMENTS We sincerely thank the anonymous reviewers and editors for their very comprehensive and constructive comments.  ... 
doi:10.1093/comjnl/bxs045 fatcat:jhk4pg47ybgjvm2eyhcypq6q5q

Using Probabilistic Topic Models in Enterprise Social Software [chapter]

Konstantinos Christidis, Gregoris Mentzas
2010 Lecture Notes in Business Information Processing  
We employ Latent Dirichlet Allocation in order to elicit latent topics and use the latter to assess similarities in resource and tag recommendation as well as for the expansion of query results.  ...  In this paper we aim to enhance the search and recommendation functionalities of ESS by extending their folksonomies and taxonomies with the addition of underlying topics through the use of probabilistic  ...  Research reported in this paper has been partially financed by the European Commission in the OrganiK project (FP7: Research for the Benefit of SMEs, 222225).  ... 
doi:10.1007/978-3-642-12814-1_3 fatcat:xp64upkfqjdj5m475454afdu3y

Sentiment Mining from Online Patient Experience using Latent Dirichlet Allocation Method

P. Padmavathy, A. Anny Leema
2016 Indian Journal of Science and Technology  
The set of latent topics is generated from emotions initially. From each of the latent topic affective terms are generated. Finally K-means clustering is applied to detect the emotion.  ...  The following six modules like Preprocessing, Topic Generation, Polarity Classification, Sentiment Classification, Sentiment Analysis and Aspect Ranking are identified in our system.  ...  Initially a distribution is chosen over a combination of topics to arbitrarily choose a topic from the topic distribution. Finally a word is generated from the topic-word distribution.  ... 
doi:10.17485/ijst/2016/v9i19/93876 fatcat:lxuhjzw4ibfsrlff7f6ofqjsku

The dual-sparse topic model

Tianyi Lin, Wentao Tian, Qiaozhu Mei, Hong Cheng
2014 Proceedings of the 23rd international conference on World wide web - WWW '14  
In this paper, we propose a dual-sparse topic model that addresses the sparsity in both the topic mixtures and the word usage.  ...  By applying a "Spike and Slab" prior to decouple the sparsity and smoothness of the document-topic and topic-word distributions, we allow individual documents to select a few focused topics and a topic  ...  Sparsity-Enhanced Topic Models Recently, there have been efforts to address the problem of sparsity in topic distributions.  ... 
doi:10.1145/2566486.2567980 dblp:conf/www/LinTMC14 fatcat:l2hba6a3mrfozhwdh4kqgzdqku

Spatial Semantic Scan: Jointly Detecting Subtle Events and their Spatial Footprint [article]

Abhinav Maurya
2016 arXiv   pre-print
the foreground topics.  ...  Many methods have been proposed for detecting emerging events in text streams using topic modeling.  ...  Semantic Scan (SS): A enhancement of the LDA topic model to detect emerging topics in text corpora. Described in detail in section (4.1). 3.  ... 
arXiv:1511.00352v3 fatcat:d5dpwaqowff3vaxydn6rnhlsgq

Emerging Research Topic Detection Using Filtered-LDA

Fuad Alattar, Khaled Shaalan
2021 AI  
In this paper, the main topic-modeling-based approaches to address this task are examined to identify limitations and necessary enhancements.  ...  Comparing two sets of documents to identify new topics is useful in many applications, like discovering trending topics from sets of scientific papers, emerging topic detection in microblogs, and interpreting  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ai2040035 fatcat:o3q4iigsqnab3m7dab7seyzeoa

Topic Modelling

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
In the history of information and technology the knowledge which was generated is stored in the form of digital technology.  ...  In this paper, the proposed Topic Modelling techniques will search based on the group of words from each document.  ...  Based on distribution each word from the document can be taken as a topic and generate new document by considering the distribution over topic.  ... 
doi:10.35940/ijitee.b1124.1292s19 fatcat:uh55rrm625cc5h26gitlxv6qxy

Hot Topic Detection and Analysis on Temporal Microblog Topic Model

Mei Yu, Hongyun Shang, Jian Yu, Tianyi Xu, Jie Gao, Yue Gao
2017 ICIC Express Letters  
In this paper, a temporal microblog topic model for detecting hot topics in microblogs is presented based on the fact that temporal changes exist in all topics.  ...  Most existing topic detection algorithms are based on n-grams clustering techniques or latent topic detection, which lack the ability to detect topics in an "on-line" manner, since they ignore the temporal  ...  The authors gratefully acknowledge the helpful comments and suggestions of the reviewers, which have greatly improved the presentation.  ... 
doi:10.24507/icicel.11.03.625 fatcat:uykv3bcydjdcvjyxlv6shf5fae

Cluster Analysis for Internet Public Sentiment in Universities by Combining Methods

Na Zheng, Jie Yu Wu
2018 International Journal of Recent Contributions from Engineering, Science & IT  
A clustering method based on the Latent Dirichlet Allocation and the VSM model to compute the text similarity is presented.  ...  The Latent Dirichlet Allocation subject models and the VSM vector space model weights strategy are used respectively to calculate the text similarity.  ...  Step2: get the parameter of the subject distribution in a document. andαis the Dirichlet distribution parameter.  ... 
doi:10.3991/ijes.v6i3.9670 fatcat:nc7vv2aywbgnnoredlmyol23y4

A Two-Stepped Feature Engineering Process for Topic Modeling using Batchwise LDA with Stochastic Variational Inference Model

Sujatha Kokatnoor, CHRIST (Deemed to be University), Balachandran Krishnan, CHRIST (Deemed to be University)
2020 International Journal of Intelligent Engineering and Systems  
hidden and relevant topics in terms of their optimized posterior distribution in hotel reviews dataset.  ...  If the input dataset is shuffled then different topics are generated leading to misleading results.  ...  Acknowledgments Authors wishes to acknowledge the technical and infrastructural help rendered by the faculty members of CSE department of CHRIST (Deemed to be University), Bangalore, India.  ... 
doi:10.22266/ijies2020.0831.29 fatcat:odfvgpa7rvbpdf2jqr55sul4ay

Hot Topic Classification of Microblogging Based on Cascaded Latent Dirichlet Allocation

Jianfeng Fu, Nianzu Liu, Cuihua Hu, Xujie Zhang
2016 Innovative Computing Information and Control Express Letters, Part B: Applications  
To address this problem, this paper presents a novel model of cascaded (two layers) latent Dirichlet allocation for hot topic classification of microblogging.  ...  The first latent Dirichlet allocation is used to find the messages posted by reply and retweet which are closely related to microblogging original content, and the second latent Dirichlet allocation is  ...  The authors also gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the presentation.  ... 
doi:10.24507/icicelb.07.03.621 fatcat:z4zlx777ljanvlzpj27rfugmyq

Feature LDA: A Supervised Topic Model for Automatic Detection of Web API Documentations from the Web [chapter]

Chenghua Lin, Yulan He, Carlos Pedrinaci, John Domingue
2012 Lecture Notes in Computer Science  
We propose a supervised generative topic model called feature latent Dirichlet allocation (feaLDA) which offers a generic probabilistic framework for automatic detection of Web APIs. feaLDA not only captures  ...  In this paper we cast the problem of detecting the Web API documentations as a text classification problem of classifying a given Web page as Web API associated or not.  ...  Acknowledgements This work was partly funded by the EU project VPH-Share (FP7-269978).  ... 
doi:10.1007/978-3-642-35176-1_21 fatcat:kgpdsys245dazefay7q4zaw7yu

Topic Categorization on Social Network Using Latent Dirichlet Allocation

Ramyadharshni S.S., Pabitha Dr.P.
2018 Bonfring International Journal of Software Engineering and Soft Computing  
The multinomial distribution of the topics is regarded as the feature of the document. The proposed system resulted in an increase in accuracy for detection of the topic categorization.  ...  to estimate the multinomial observation and each topic is categorized by a probabilistic distribution over the words.  ...  CONCLUSION The proposed system clearly states that there is an efficient increase in the detection of topic categorization using Latent Dirichlet allocation (LDA).  ... 
doi:10.9756/bijsesc.8390 fatcat:wtbwyzzaqbbhfhwowr3lazbi2q
« Previous Showing results 1 — 15 out of 6,691 results