@article{._2016, place={india}, title={Text Summarization using topic modeling and cluster based MapReduce framework}, volume={5}, url={http://ijecs.in/index.php/ijecs/article/view/3393}, abstractNote={<p><strong><em>Document summarization provides an instrument for faster understanding the collection of text documents and has a number of real life applications. Semantic similarity and clustering can be utilized efficiently for generating effective summary of large text collections. Summarizing large volume of text is a challenging and time consuming problem particularly while   considering the semantic similarity computation in   summarization  process.   Summarization   of   text   collection   involves   intensive   text   processing   and computations to generate the summary. MapReduce is proven state of art technology for handling Big Data. In this  paper,  a  novel  framework based  on  MapReduce technology is  proposed for  summarizing large  text collection. The proposed technique is designed using semantic similarity based clustering and topic modeling using Latent Dirichlet Allocation (LDA) for summarizing the large text collection over MapReduce framework. The summarization task is  performed in  four stages and provides a modular implementation of multiple documents summarization. The  presented technique is  evaluated  in  terms  of  scalability and  various  text summarization parameters namely, compression ratio, retention ratio, ROUGE and Pyramid score are also measured. The advantages of MapReduce framework are clearly visible from the Experiments and it is also demonstrated that MapReduce provides a faster implementation of summarizing large text collections and is a powerful tool in Big Text Data analysis.</em></strong></p>}, number={12}, journal={International Journal of Engineering and Computer Science}, author={., N.Prameela}, year={2016}, month={Nov.} }