@article{2469,
  author = {Zar Zar Wint, Theo Ducros, Masayoshi Aritsugi},
  title = {Non-words Spell Corrector of Social Media Data in Message Filtering Systems},
  journal = {Journal of Digital Information Management},
  year = {2018},
  volume = {16},
  number = {2},
  doi = {https://doi.org/10.6025/jdim/2018/16/2/64-75},
  url = {http://dline.info/fpaper/jdim/v16i2/jdimv16i2_2.pdf},
  abstract = {We develop an extended version of spell
checker and corrector to check non-word errors in social
media datasets, which will be used in message filtering
systems especially for cyberbullying detection. We use
the dictionary techniques to check words, twelve-word spell
error checking and correction approaches to correct the
non-word errors, and n-gram and Levenshtein distance to
select the most suitable word among corrected words. If
there is more than one corrected word we get from each
approach, we use n-gram techniques to choose the corrected
and reasonable word from the words in n-gram
database. When we used the Levenshtein distance in our
previous work, we found that it selected the first corrected
word and it was not a reasonable one in some sentences.
Therefore, we use the n-gram database in this paper.},
}