Loading [a11y]/accessibility-menu.js
Towards Ethical Content-Based Detection Of Online Influence Campaigns | IEEE Conference Publication | IEEE Xplore

Towards Ethical Content-Based Detection Of Online Influence Campaigns


Abstract:

The detection of clandestine efforts to influence users in online communities is a challenging problem with significant active development. We demonstrate that features d...Show More

Abstract:

The detection of clandestine efforts to influence users in online communities is a challenging problem with significant active development. We demonstrate that features derived from the text of user comments are useful for identifying suspect activity, but lead to increased erroneous identifications (false positive classifications) when keywords over-represented in past influence campaigns are present. Drawing on research in native language identification (NLI), we use “named entity masking” (NEM) to create sentence features robust to this shortcoming, while maintaining comparable classification accuracy. We demonstrate that while NEM consistently reduces false positives when key named entities are mentioned, both masked and unmasked models exhibit increased false positive rates on English sentences by Russian native speakers, raising ethical considerations that should be addressed in future research.
Date of Conference: 13-16 October 2019
Date Added to IEEE Xplore: 05 December 2019
ISBN Information:
Print on Demand(PoD) ISSN: 1551-2541
Conference Location: Pittsburgh, PA, USA

Contact IEEE to Subscribe

References

References is not available for this document.