Detecting Irregularities in Blog Comment Language Affecting POS Tagging Accuracy

Download Now Free registration required

Executive Summary

Studying technology acceptance requires the survey and analysis of user opinions to identify acceptance-relevant factors. In addition to surveys, Web 2.0 poses a huge collection of user comments regarding different technologies. Extracting acceptance-relevant factors and user opinions from such comments requires the application of Natural Language Processing (NLP) methods, particularly Part-Of-Speech (POS) tagging. Applied to typical blog language POS tagging often suffers from high error rates. In this paper, the authors present multiple user-specific studies of blog comments to analyze the relation between blog language and performance of NLP methods.

  • Format: PDF
  • Size: 457.77 KB