@article{2470,
  author = {Abhishek Kumar Singh, Naresh Kumar Nagwani, Sudhakar Pandey},
  title = {Efficient Management of Community Question Answering Sites using Improved Spectral Clustering},
  journal = {Journal of Digital Information Management},
  year = {2018},
  volume = {16},
  number = {2},
  doi = {https://doi.org/10.6025/jdim/2018/16/2/76-84},
  url = {http://dline.info/fpaper/jdim/v16i2/jdimv16i2_3.pdf},
  abstract = {Community Question-Answering(CQA) sites
are the major platform where posts are generated by peers
in the form of questions and answers for information seeking
in online environments. In general, multiple posts are
created by different users on a particular topic or subject.
Large number of posts raises the difficulties in information
management of these sites. A number of approaches
are suggested in recent research work for efficient management
of data for CQA sites. Many of the existing approaches
have suggested use of clustering techniques
for managing the CQA sites, but ignored the tagging data
(user tags) of the posts. In this paper, an improved spectral
clustering technique is derived based on similarity
measures for text processing (SMTP) and utilized for clustering
the posts considering the tagging data available on
CQA sites. A specialized data structure, namely,
folksonomy is developed for clustering using the relationship
between tags, posts and users.The proposed method
is developed in two stages. In first stage, the folksonomy
relation is created and post similarity graph is built with
the help of tag frequency-inverse post frequency. In the
second stage, the spectral clustering algorithm is applied
to the post similarity matrix to group the similar posts.
The post clusters are generated as the output of the proposed
algorithm where the post information management
can be made with the help of user tags. The experimental
results show that the improvedspectral clustering algorithm
outperforms the other considered clustering algorithms with a huge margin and it will be helpful for information
management of the CQA sites. The improved spectral
clustering algorithm will be useful for post pre-processing,
faster information retrieval, duplicate posts identification
and posts management from clusters.},
}