Filters








3,899 Hits in 3.7 sec

Semrank

Jagrati Singh, Anil Kumar Singh
2021 International Journal of Cognitive Informatics and Natural Intelligence  
To handle these challenges, the authors introduce a new approach for computing the relative tweet importance based on the concept of the Pagerank algorithm where adjacency matrix of the graph representation  ...  of tweets contains semantic similarity matrix based on the word mover's distance measure utilizing Word2Vec word embedding model.  ...  -1 R-2 R Graph-based ranking algorithms are based on the global importance of a node within the entire graph.  ... 
doi:10.4018/ijcini.20210701.oa6 fatcat:iknjhifxircpzjahn6d4ccfqey

NSLPCD: Topic based tweets clustering using Node significance based label propagation community detection algorithm

Jagrati Singh, Anil Kumar Singh
2020 Annals of Mathematics and Artificial Intelligence  
Based on these defined keywords, the keyword co-occurrence graph is built, and subsequently, the NSLPCD algorithm is applied to get topic clusters in the form of communities.  ...  The proposed algorithm analyzes the frequency distribution of keywords in the collection of tweets and finds two types of keywords: topic-identifying and topic-describing keywords, which play an important  ...  Zhao et al [22] proposed a summarization framework based on the word dependency graph approach, in which nodes represent keywords and edges represent dependency grammar relation between keywords.  ... 
doi:10.1007/s10472-020-09709-z pmid:32989349 pmcid:PMC7511268 fatcat:earpw3jhorfxfphtulvpuvmkru

Detecting and Summarizing Emergent Events in Microblogs and Social Media Streams by Dynamic Centralities [article]

Neela Avudaiappan, Alexander Herzog, Sneha Kadam, Yuheng Du, Jason Thatcher, Ilya Safro
2016 arXiv   pre-print
We present a system for monitoring emergent keywords and summarizing a document stream based on the dynamic semantic graphs of streaming documents.  ...  We introduce the notion of dynamic eigenvector centrality for ranking emergent keywords, and present an algorithm for summarizing emergent events that is based on the minimum weight set cover.  ...  Acknowledgments We thank the Clemson CBBS One-Year accelerate grant program for providing funds for this research.  ... 
arXiv:1610.06431v1 fatcat:b4kodlb6p5ewdiu7te74pmszpm

Summarizing sporting events using twitter

Jeffrey Nichols, Jalal Mahmud, Clemens Drews
2012 Proceedings of the 2012 ACM international conference on Intelligent User Interfaces - IUI '12  
We evaluate our algorithm compared to human-generated summaries and the previous best summarization algorithm, and find that the results of our method are superior to the previous algorithm and approach  ...  Temporal cues, such as spikes in the volume of status updates, are used to identify the important moments within an event, and a sentence ranking method is used to extract relevant sentences from the corpus  ...  Tweets for this dataset were recorded through Twitter's Streaming API using a track stream that receives tweets based on keyword query.  ... 
doi:10.1145/2166966.2166999 dblp:conf/iui/NicholsMD12 fatcat:6ucs6oo6j5ay5gwojwrgwazbsu

GeoBurst

Chao Zhang, Guangyu Zhou, Quan Yuan, Honglei Zhuang, Yu Zheng, Lance Kaplan, Shaowen Wang, Jiawei Han
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
We propose GEOBURST, a method that enables effective and real-time local event detection from geo-tagged tweet streams.  ...  bursty ones.  ...  and the semantic side is captured using random walk on a keyword co-occurrence graph.  ... 
doi:10.1145/2911451.2911519 dblp:conf/sigir/ZhangZYZZKWH16 fatcat:uzuccddjwnb6hnph5fllgo47ri

Keyword Based Tweet Extraction and Detection of Related Topics

Amrutha Benny, Mintu Philip
2015 Procedia Computer Science  
Our research work is to propose a method, which collect tweets using a specific keyword and then, summarizes them to find out topics related to that keyword.  ...  Twitter is a micro blogging site that helps the transfer of information as short length tweets. The large quantum of information makes it necessary to find out methods and tools to summarize them.  ...  One of the main Objectives of the proposed system is to summarize and cluster the tweets based upon certain keywords. The keywords can be any noun in English about which the user wants to know.  ... 
doi:10.1016/j.procs.2015.02.032 fatcat:24sckwcuoffwvmft5pwv664wgi

Multi-tweet Summarization of Real-Time Events

Muhammad Asif Hossain Khan, Danushka Bollegala, Guangwen Liu, Kaoru Sezaki
2013 2013 International Conference on Social Computing  
We have proposed a graph-based retrieval algorithm that identifies tweets with popular discussion points among the set of tweets returned by Twitter search engine in response to a query comprising the  ...  In this paper, we propose a method for multi-tweet summarization of an event. It allows the search users to quickly get an overview about the important moments of the event.  ...  One of the most famous graph-based ranking algorithm, the PageRank [15] , is based on intuitive notion of endorsement.  ... 
doi:10.1109/socialcom.2013.26 dblp:conf/socialcom/KhanBLS13 fatcat:ucaxlrwbbvd6fnpavmxldjb2iq

OntoRealSumm : Ontology based Real-Time Tweet Summarization [article]

Piyush Kumar Garg and Roshni Chakraborty and Sourav Kumar Dandapat
2022 arXiv   pre-print
Therefore, we propose an ontology based real-time tweet summarization (OntoRealSumm) for disasters which generates a summary of the tweets related to disasters with minimum human intervention.  ...  Given tweets related to a disaster, OntoRealSumm ensures fulfilment of the objectives related to disaster tweet summarization, such as identification of a category of each tweet and summarization of each  ...  Most of the existing extractive tweet summarization approaches can further be segregated based on their proposed methodology into graph based [17] , content based [71] , deep learning approaches [15  ... 
arXiv:2201.06545v1 fatcat:ym577vkzavflxa5iqzbgruqgf4

An Analysis of COVID-19 Knowledge Graph Construction and Applications [article]

Dominic Flocco, Bryce Palmer-Toy, Ruixiao Wang, Hongyu Zhu, Rishi Sonthalia, Junyuan Lin, Andrea L. Bertozzi, P. Jeffrey Brantingham
2021 arXiv   pre-print
Further analysis on the constructed knowledge graph provides insight into how tweets reflect public sentiments towards COVID-19 related topics and how changes in these sentiments correlate with real-world  ...  In this paper we present a knowledge graph constructed from COVID-19 related tweets in the Los Angeles area, supplemented with federal and state policy announcements and disease spread statistics.  ...  We implement an algorithm that yields aspect-based sentiment scores based on VADER. Given a tweet and a set of keywords appearing in the tweet, the algorithm performs the following steps.  ... 
arXiv:2110.04932v1 fatcat:ctnfyr3hcfgytlc7kx4iltlxgu

Event Detection and Summarization Based on Social Networks and Semantic Query Expansion

Sathiyamurthy K, Shanmugavalli G, Udayalakshmi N
2014 International Journal on Natural Language Computing  
Event summarization provides a comprehensible explanation of the event sequence based on certain aspects.  ...  Intuitively, documents describing the same event will contain similar sets of keywords, and the graph for a document collection will contain clusters individual events.  ...  A work on summarizing Sporting Events Using Twitter was done based on an automated method for implicitly crowd sourcing summaries of events using only status updates posted to Twitter as a source [8]  ... 
doi:10.5121/ijnlc.2014.3602 fatcat:okd6f2bpdberrpdvzan3ac6ix4

EviDense: a Graph-based Method for Finding Unique High-impact Events with Succinct Keyword-based Descriptions [article]

Oana Balalau, Carlos Castillo, Mauro Sozio
2019 arXiv   pre-print
We evaluate our approach on a large collection of tweets posted over a period of 19 months, using a crowdsourcing platform.  ...  We present EviDense, a graph-based approach for finding high-impact events (such as disaster events) in social media.  ...  E D D : a Graph-based Method for Finding Unique High-impact Events with Succinct Keyword-based Descriptions 3 , we obtain a 95% confidence interval on the percentage of duplicate events, i.e. the DERate  ... 
arXiv:1912.02484v1 fatcat:aizs4cvacrhbdnkd4ep5r4qqty

Complaint Analysis in Indonesian Language Using WPKE and RAKE Algorithm

Rini Wongso, Novita Hanafiah, Jaka Hartanto, Alexander Kevin, Charles Sutanto, Fiona Kesuma
2018 International Journal of Electrical and Computer Engineering (IJECE)  
In this research, we proposed a method to extract keywords from tweets in Indonesian language, WPKE.  ...  Finally, we develop a method to do clustering to groups the topics of complaints with data set obtained from Twitter using the "komplain" hashtag.  ...  The co-occurences of selected words are accumulated within a word co-occurrence graph and TextRank (a graph-based ranking algorithm) are used to rank the words based on their associations in the graph.  ... 
doi:10.11591/ijece.v8i6.pp5311-5317 fatcat:jvr6mmjztfd2hpjdr2wr6d5lqm

Summarizing Situational and Topical Information During Crises [article]

Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran, Prasenjit Mitra
2016 arXiv   pre-print
and then follows a word graph and concept event based abstractive summarization technique to produce the final summary.  ...  A summary is generated using a two stage framework that first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique  ...  Rudra was supported by a fellowship from Tata Consultancy Services.  ... 
arXiv:1610.01561v1 fatcat:qrvz63akrnepnec77kr4r3w3la

Event Detection and Retrieval on Social Media [article]

Manos Schinas, Symeon Papadopoulos, Yiannis Kompatsiaris, Pericles Mitkas
2018 arXiv   pre-print
In this chapter, we present several research efforts from recent years that tackle two main problems: a) event detection and b) event-based media retrieval and summarization.  ...  Given a target event the goal of event summarization is first to identify relevant content and then to represent it in a concise way, selecting the most appealing and representative content.  ...  Then, it applies a graph-based technique to extract important sentences from the tweets around these moments.  ... 
arXiv:1807.03675v1 fatcat:x3dgrhj6k5ewbb5gwm3vmi7khm

Trendspedia: An Internet observatory for analyzing and visualizing the evolving web

Wei Kang, Anthony K. H. Tung, Wei Chen, Xinyu Li, Qiyue Song, Chao Zhang, Feng Zhao, Xiajuan Zhou
2014 2014 IEEE 30th International Conference on Data Engineering  
Three of them aim to enrich each Wikipedia entity by analyzing the relevant contents while the other one builds an information network among the most relevant Wikipedia entities.  ...  In this paper, we present a novel system which brings proper context to continuously incoming social media contents, such that mass information can be indexed, organized and analyzed around Wikipedia entities  ...  Thus, keywords in a Formal Concept naturally serve as a summary of the tweets. Our tweets summarization approach has the following characteristics: (1) Efficient.  ... 
doi:10.1109/icde.2014.6816742 dblp:conf/icde/KangTCLSZZZ14 fatcat:o34q2t7wlndkljtgd2umdlqi6a
« Previous Showing results 1 — 15 out of 3,899 results