Advertisement

Some Syntax-Only Text Feature Extraction and Analysis Methods for Social Media Data

  • Monte Hancock
  • Charles Li
  • Shakeel RajwaniEmail author
  • Payton Brown
  • Olivia Hancock
  • Corinne Lee
  • Yaniv Savir
  • Nicolas Nuon
  • Francesca Michaels
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10284)

Abstract

Automated characterization of online social behavior is becoming increasingly important as day-to-day human interaction migrates from expensive “real world” encounters to less expensive virtual interactions over computing networks. The effective automated characterization of human interaction in social media has important political, economic, social applications.

New analytic concepts are presented for the extraction and enhancement of salient numeric features from unstructured text. These concepts employ relatively simple syntactic metrics for characterizing and distinguishing human and automated social media posting behaviors. The concepts are domain agnostic, and are empirically demonstrated using posted text from a particular social medium (Twitter).

An innovation uses a feature-imputation regression method to perform feature sensitivity analysis.

Keywords

Twitter Text processing Social media Feature selection 

References

  1. 1.
    Hancock, M., et al.: Modeling of social media behaviors using only account metadata. In: 8th International Conference on Applied Human Factors and Ergonomics, Orlando, Florida, July 2016Google Scholar
  2. 2.
    Hancock, M., et al: Multi-cultural empirical study of password strength vs. ergonomic utility. In: 18th International Conference on Human Computer Interaction, Toronto, Canada, July 2016Google Scholar
  3. 3.
    Hancock, M., et al.: Field-theoretic modeling method for emotional context in social media: theory and case study. In: Schmorrow, D.D., Fidopiastis, C.M. (eds.) AC 2015. LNCS (LNAI), vol. 9183, pp. 418–425. Springer, Cham (2015). doi: 10.1007/978-3-319-20816-9_40 CrossRefGoogle Scholar
  4. 4.
    Hancock, M., Sessions, C., Lo, C., Rajwani, S., Kresses, E., Bleasdale, C., Strohschein, D.: Stability of a type of cross-cultural emotion modeling in social media. In: Schmorrow, D.D., Fidopiastis, C.M. (eds.) AC 2015. LNCS (LNAI), vol. 9183, pp. 410–417. Springer, Cham (2015). doi: 10.1007/978-3-319-20816-9_39 CrossRefGoogle Scholar
  5. 5.
    Hancock, M.: Novel methods for adjudicating multiple cognitive decision models. In: 2nd International Augmented Cognition Conference, San Francisco, CA, October 2006Google Scholar
  6. 6.
    Hancock, M., Day, J.: Exploring human cognition by spectral decomposition of a Markov random field. In: 1st International Augmented Cognition Conference, Las Vegas, NV, July 2005Google Scholar
  7. 7.
    Hancock, M.: A cognitive engineering methodology for building multi-level fusion applications. In: Northrop Grumman Data Fusion Conference, Aurora, CO, November 2007Google Scholar
  8. 8.
    Hancock, M.: Automating the characterization of social media culture, social context, and mood. In: Science of Multi-Intelligence Conference (SOMI), Chantilly, VA (2014)Google Scholar
  9. 9.
    Hancock, M.: Data mining: technology and practice in the real world. In: Tutorial Notes of the SIAM International Data Mining Conference (SDM 2003) (2003)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Monte Hancock
    • 1
  • Charles Li
    • 2
  • Shakeel Rajwani
    • 3
    Email author
  • Payton Brown
    • 3
  • Olivia Hancock
    • 3
  • Corinne Lee
    • 3
  • Yaniv Savir
    • 3
  • Nicolas Nuon
    • 3
  • Francesca Michaels
    • 3
  1. 1.4Digital Inc.Webster UniversityMelbourneUSA
  2. 2.Mercy CollegeDobbs FerryUSA
  3. 3.Sirius 17B TeamMelbourneUSA

Personalised recommendations