Filters








88,967 Hits in 6.3 sec

Learning from the News: Predicting Entity Popularity on Twitter [article]

Pedro Saleiro, Carlos Soares
2016 arXiv   pre-print
In this work, we tackle the problem of predicting entity popularity on Twitter based on the news cycle.  ...  We apply a supervised learn- ing approach and extract four types of features: (i) signal, (ii) textual, (iii) sentiment and (iv) semantic, which we use to predict whether the popularity of a given entity  ...  We applied a monthly sliding window setting in which we start by predicting entity popularity for every day of January 2015 (i.e. the test set) using a model trained on the previous 24 months, 730 days  ... 
arXiv:1607.03057v1 fatcat:4xwqf67wa5gs7oiluiuq7zhbhu

Finding Potential News from Trends Originating in the Blogosphere

Nigel Dewdney
2015 Research in Computing Science  
Tracking current population interests by trends in online media of entities and topics has become increasingly popular.  ...  Results show that many trends do originate in blogs, with approximately 12% seen subsequently in news media. Frequency based ranking provides a basis for selecting the most predictive trends.  ...  [18] in comparing the most popular named entities in news and blogs on a mentions-per-day basis found a small percentage of topics discussed in blogs existed before corresponding news-stories were published  ... 
doi:10.13053/rcs-90-1-20 fatcat:a4q5gwz3vverxmvzbfprxabr4y

PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity [article]

Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang
2021 arXiv   pre-print
Besides, we propose a popularity-aware user encoder to eliminate the popularity bias in user behaviors for accurate interest modeling.  ...  In our method, the ranking score for recommending a candidate news to a target user is the combination of a personalized matching score and a news popularity score.  ...  We are grateful to Xing Xie, Tao Di, and Wei He for their insightful comments and discussions.  ... 
arXiv:2106.01300v2 fatcat:cg6xzv3y4rdhzcjcclv4efgaaq

Are Most-Viewed News Articles Most-Shared? [chapter]

Yangjie Yao, Aixin Sun
2013 Lecture Notes in Computer Science  
Through topic modeling and named entity analysis, we observe that economy news is more likely to be shared and sports news is less likely to be shared or commented.  ...  Specifically, we focus on the sets of most-viewed, most-shared, and mostcommented news published by a major news agency for about two months.  ...  Another reason for not being able to identify a topic is that, a name entity extracted is not a full name (e.g., Berry).  ... 
doi:10.1007/978-3-642-45068-6_35 fatcat:osilokzeznap7cda6fg7ngvjgi

Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions

Wei Shen, Jianyong Wang, Jiawei Han
2015 IEEE Transactions on Knowledge and Data Engineering  
However, this task is challenging due to name variations and entity ambiguity.  ...  Entity linking is the task to link entity mentions in text with their corresponding entities in a knowledge base.  ...  This model incorporates three types of heterogeneous knowledge (i.e., popularity knowledge, name knowledge, and context knowledge) into a unified probabilistic model for the entity linking task.  ... 
doi:10.1109/tkde.2014.2327028 fatcat:h6neohummbgf3agcpirvzru4ry

#Bieber + #Blast = #BieberBlast: Early Prediction of Popular Hashtag Compounds

Suman Kalyan Maity, Ritvik Saraf, Animesh Mukherjee
2016 Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing - CSCW '16  
We identify reasons for this compounding and propose a prediction model that can identify with 77.07% accuracy if a pair of hashtags compounding in the near future (i.e., 2 months after compounding) shall  ...  become popular.  ...  Chris Biemann, TU Darmstadt for providing them with a historical Twitter 1% random sample data.  ... 
doi:10.1145/2818048.2820019 dblp:conf/cscw/MaitySM16 fatcat:hwwu4l7de5b5xnsgvktprggjc4

OLAPing social media

Nafees Ur Rehman, Andreas Weiler, Marc H. Scholl
2013 Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining - ASONAM '13  
Users express their feelings and opinions on every topic of interest.  ...  These opinions carry import value for personal, academic and commercial applications, but the volume and the speed at which these are produced make it a challenging task for researchers and the underlying  ...  The model that we discuss here is a tweet popularity classifier. It is a decision tree based classification and prediction model that we developed based on the dataset presented in Figure 3 .  ... 
doi:10.1145/2492517.2500273 dblp:conf/asunam/RehmanWS13 fatcat:4tyig4m4ozh77d66vjjeyr2ove

Entity Network Prediction Using Multitype Topic Models

H. SHIOZAKI, K. EGUCHI, T. OHKAWA
2008 IEICE transactions on information and systems  
Statistical models that capture dependencies between named entities and topics can play an important role.  ...  We show that this multitype topic model performs better at making predictions on entity networks, in which each vertex represents an entity and each edge weight represents how a pair of entities at the  ...  Acknowledgements We thank Giridhar Kumaran, University of Massachusetts Amherst, for providing the annotation data.  ... 
doi:10.1093/ietisy/e91-d.11.2589 fatcat:ccrbafp6i5gedkxceeyhk3iwia

Leveraging Global and Local Topic Popularities for LDA-Based Document Clustering

Peng Yang, Yu Yao, Huajian Zhou
2020 IEEE Access  
In this paper, we propose a probabilistic model named tpLDA, which incorporates different levels of topic popularity information to determine the prior LDA distribution, discover the latent topics and  ...  A wide range of computational traditional topic models, such as LDA (Latent Dirichlet Allocation) and its variants, have made great progress.  ...  The authors would also like to thank the anonymous reviewers for their valuable comments and suggestions, which were helpful for improving the quality of the paper.  ... 
doi:10.1109/access.2020.2969525 fatcat:2yzrxi7nnbey3jkjxwxos4a74u

XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference [article]

Xinyu Hua, Lei Li, Lifeng Hua, Lu Wang
2020 arXiv   pre-print
Nonetheless, this remains a challenging task due to limited context and diverse name variations. In this paper, we study the problem of entity linking for Chinese news comments given mentions' spans.  ...  Automatic identification of mentioned entities in social media posts facilitates quick digestion of trending topics and popular opinions.  ...  Conclusion We present a novel entity linking model, XREF, for Chinese online news comments.  ... 
arXiv:2006.14017v1 fatcat:y33ypyyhyrdw5fktn7b25ntusy

Named entity recognition in query

Jiafeng Guo, Gu Xu, Xueqi Cheng, Hang Li
2009 Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval - SIGIR '09  
We consider contexts of a named entity (i.e., the remainders of queries after the named entity is removed) as words of a document, and classes of the named entity as topics.  ...  This paper addresses the problem of Named Entity Recognition in Query (NERQ), which involves detection of the named entity in a given query and classification of the named entity into predefined classes  ...  In the topic model, a named entity corresponds to a document, contexts of a named entity correspond to words of the document, classes of a named entity correspond to topics of the model.  ... 
doi:10.1145/1571941.1571989 dblp:conf/sigir/GuoXCL09 fatcat:xobbhgvcnnfelca6nvyxcw3t3i

Location-Aware Personalized News Recommendation Based on Behavior and Popularity Technique

Hengane Shubham
2020 International Journal for Research in Applied Science and Engineering Technology  
Then, considers the scope of the user's preferences for historical news, and propose a method to calculate the desire weight of historic news consistent with the user's analyzing behavior and the popularity  ...  Now-a-days people can read news from several sources around the world. This paper investigates a novel user profile model to express users' preferences from different aspects.  ...  Mathematical Model 1) User Profile Construction: Construct the profile of the user by three different but related stages: News keywords, News named entities, and News topic distributions.  ... 
doi:10.22214/ijraset.2020.27921 fatcat:arvlxufr6faczfwznrfsvzumr4

NewsMiner: Multifaceted news analysis for event search

Lei Hou, Juanzi Li, Zhichun Wang, Jie Tang, Peng Zhang, Ruibing Yang, Qian Zheng
2015 Knowledge-Based Systems  
base and social content), and introduce a unified probabilistic model for topic extraction and inner relationship discovery within events.  ...  We further present a multifaceted ranking strategy to rank the linked events, topics and entities simultaneously.  ...  It's important to note that we take the news articles in a specific event as the model input so that we named it eventbased entity topic model.  ... 
doi:10.1016/j.knosys.2014.11.017 fatcat:kcv3wemrazbirnerabgz2fbuee

Predicting event-relatedness of popular queries

Seyyedeh Newsha Ghoreishi, Aixin Sun
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Our analysis shows that the number of named entities in search results and their appearances in Wikipedia are among the most discriminative features for query event-relatedness prediction.  ...  In this paper, we identify 20 features including both contextual and temporal features from a small set of search results of a query and predict its event-relatedness.  ...  We therefore consider the number of Named Entities (NE) as a feature for query eventrelatedness prediction.  ... 
doi:10.1145/2505515.2507853 dblp:conf/cikm/GhoreishiS13 fatcat:agypapk3bngm7j3y3zjn725vky

To Post or Not to Post

Sofiane Abbar, Carlos Castillo, Antonio Sanfilippo
2018 Proceedings of the 29th on Hypertext and Social Media - HT '18  
In this paper, we propose a new approach for predicting the popularity of news articles before they go online.  ...  Second, the popularity of the new article is related to the recent historical popularity of its main topic.  ...  We introduce a new method for early prediction of popularity of news articles that combines article topicality and article similarity.  ... 
doi:10.1145/3209542.3209575 dblp:conf/ht/Abbar0S18 fatcat:ffk5zdouwbdlpoulotuqjgunii
« Previous Showing results 1 — 15 out of 88,967 results