Corpus ID: 36282768

Towards Automatic Analyses of Police Interviews – Machine Learning of Question Types

  title={Towards Automatic Analyses of Police Interviews – Machine Learning of Question Types},
  author={Christian Spijkerboer},
One of the indicators for the quality of a police interrogation is the type of questions the interviewer asks. Can machine learning be used to automatically tell what type of question is meant by the utterance of the interviewer? Using a multidimensional annotation scheme for question types, an annotated corpus of interviews is developed. Various feature sets and machine learning techniques are tested to explore how well a machine can distinguish the question types. Through experimenting with… Expand
1 Citations

Tables from this paper

Question Answer Matching in Police Witness Interviews : A Machine Learning Approach
  • Kevin Hetterscheid
  • 2017
  • Highly Influenced


Question Terminology and Representation for Question Type Classification
  • 21
  • PDF
The question of question types in police interviews: A review of the literature from a psychological and linguistic perspective.
  • 100
  • Highly Influential
Police interviews with suspected paedophiles: a discourse analysis
  • 22
Towards a ‘Science’ of Corpus Annotation: A New Methodological Challenge for Corpus Linguistics
  • 49
  • Highly Influential
  • PDF
A review in feature extraction approach in question classification using Support Vector Machine
  • 14
  • Highly Influential
Recognizing emotions in text using ensemble of classifiers
  • 97
  • Highly Influential
Dialogue Act Recognition Approaches
  • 30
  • Highly Influential
  • PDF