As part of an ongoing standardization effort, we were asked to evaluate Marathi text input mechanisms on smartphones. We undertook a between-subject longitudinal evaluation of four existing keyboards with 153 novice users who participated for 31 sessions each, spread over 3–4 weeks. In this paper, we present the empirical results of the performance of these keyboards and discuss them with respect to their designs. We found that keyboards with logical layouts performed marginally better than keyboards with partially frequency-based layouts. Results also showed that users performed poorly on keyboards that have word prediction features in comparison with keyboards that don’t have prediction features while typing Marathi. We speculate that this difference in performance is related to a “cognitive toll” that the users pay to use word prediction. We identify several directions for future research.

My Contribution

  Iterative design
  Data Analysis
  Usability Study
  Database Management

Keyboards Selected

          swiftkey                           Inscript                           Sparsh                               Swarachakra

InScript Swiftkey Swarachakra Sparsh
Layout Frequency + partly Logical Frequency + partly Logical Logical Logical
Shifted layout Yes (on shift or long-press) Yes (on shift or long-press) No Only two conjuncts on the shifted layout
Pop-up No No Yes (circular pop-up pie-menu of vowel modifiers) Yes (rectangle pop-up menu of vowel modifiers)
Word Completion No Yes No yes
Word Prediction No Yes No No
Touch gestures Tap, long press Tap, long press, swipe Tap, tap and slide Tap, tap and slide

Outcome of study

  Longitudinal data of Speed performance on all the keyboards across 300 phrases.
  Summary of median session wise accuracy for all the session.
  Corrected and Uncorrected error rate of each keyboard session wise.
  Number of predictions picked, available and words to be typed by users on Swiftkey and Sparsh keyboards.
  Comparison of mean speeds (CPM) of the keyboards