Text Analytics

  • Vadim Kagan
  • Edward Rossini
  • Demetrios Sapounas
Part of the SpringerBriefs in Computer Science book series (BRIEFSCOMPUTER)


The exponential growth in the use of social media and creation of unstructured data has elevated the importance of text analysis technologies. From political campaigns to business intelligence and national security, the need for the automated extraction of information from unstructured textual data has led to the development of a number of specialized approaches to address the unique needs of particular markets. This project takes a unique approach, which applies text analysis techniques to detection of psychological signals that may be symptomatic of Post-Traumatic Stress Disorder (PTSD). While standard text analysis technologies have been used, this particular project required heavy customization of the toolset. The Text-in, Data-out (TIDO) tool, built to facilitate the human annotation of the training corpus, has been used to capture the human psychologists’ knowledge and make it available to the analytical engine for training.


Ptsd Symptom Latent Dirichlet Allocation Sentiment Analysis Human Annotation Psychological Signal 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Luhn HP (1958) A business intelligence system, IBM Journal of Research and Development, Volume 2 Issue 4, October 1958, Pages 314–319Google Scholar
  2. 2.
    Cesarano C, Dorr B, Picariello A, Reforgiato D, Sagoff A, Subrahmanian VS (2006) OASYS: an opinion analysis system. Proceedings of AAAI-2006 spring symposium on computational approach to analyzing weblogsGoogle Scholar
  3. 3.
    Sleator D, Temperley D (1991) Parsing English with a link grammar. Carnegie Mellon University Computer Science technical report, CMU-CS-91-196Google Scholar
  4. 4.
    Subrahmanian VS, Reforgiato D (2008) AVA: adjective-verb-adverb combinations for sentiment analysis. Intell Syst 23(4)Google Scholar
  5. 5.
    Ananiadou S, McNaught J (eds) (2006) Text mining for biology and biomedicine. Artech House, Boston, MA, pp 43–66Google Scholar
  6. 6.
    Richardson M et al (2010) Using SAS® Text Miner 4.1 to create a term list for patients with PTSD within the VA. SESUG 2010: The Proceedings of the SouthEast SAS Users Group, Savannah, GeorgiaGoogle Scholar
  7. 7.
    Blei D et al (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022MATHGoogle Scholar
  8. 8.
    Blei DM, Lafferty JD (2006) Correlated topic models. In: Weiss Y, Schölkopf B, Platt J (eds) Advances in neural information processing systems 18. MIT Press, Cambridge, MAGoogle Scholar
  9. 9.
    Wei X, Bruce Croft W (2006) LDA-based document models for ad-hoc retrieval. Proceedings of the 29th annual international ACM SIGIR conference on research and development in information retrieval, 6–11 August 2006, Seattle, WAGoogle Scholar

Copyright information

© The Author(s) 2013

Authors and Affiliations

  • Vadim Kagan
    • 1
  • Edward Rossini
    • 2
  • Demetrios Sapounas
    • 3
  1. 1.SentiMetrix©, Inc.BethesdaUSA
  2. 2.Roosevelt UniversityChicagoUSA
  3. 3.Center for International RehabilitationWashington, DCUSA

Personalised recommendations