A data set for the investigation of the effects of audio-reinforcement on recollection rates of e-learning users

This is a data set for the investigation of the effects of audio-reinforcement on recollection rates of e-learning users. It contains two kinds of data as (i) audio files and (ii) activity log files. Note that the raw data set contains privacy sensitive information, which is concealed in this release.

Audio files

The audio stimuli are recorded from a Japanese mother-tongue speaker. In total, the speaker uttered 504 words and 118 numbers. In each recording session, we displayed a sequence of images, which is either a word or a number on the screen of a notebook PC to the speaker [1]. Together with the sequence of images, a single audio clip is recorded for each image (i.e. text).  Note that both the sequence of images and the audio recording are executed through programs implemented in Python. After the recording sessions were finished, the audio clips are post-processed such that the silence segments are cropped and padded.

Activity log files

The activity log files are recorded from the e-learning software Anki [2]. They contain two basic kinds of information as (i) temporal and (ii) identifier.

The temporal variables are registered in  UNIX time at millisecond resolution and include \(t_p\), \(t_f\), and \(t_e\). Here, \(t_p\) denotes the time of prompt, i.e. the instant when the Q-face of a card appears. In addition,  \(t_f\) represents the time of flip, i.e. the instant when the learner presses the ''Show Answer'' button and discloses the A-face of the card. Finally,  \(t_e\) stands for the time of evaluation, i.e. the instant when the learner assesses the difficulty of a card by choosing one of  ''Again'', ''Good'' or ''Easy''.

On the other hand, the identifier variables are integer codes used to determine the deck or card that is being studied (i.e.displayed) at a given time instant (e.g. deck ID, card ID). Note that each log file is associated with a single user. Namely, the software recorded one log file into the account of each user. In addition, each line of the activity log file  corresponds to a single action of the user which is considered as a reaction to the software. The structure of each line of data is as follows:  [unix time], function name, data in detail (i.e. flags, queue).

The data set is used as an input for building the estimator model in our article [3].

Reference:

[1] P. Supitayakul, Displaying visual stimuli and recording audio, https://github.com/Parisa-S/Displaying-visual-stimuli-and-recording-audio.

[2] D. Elmes, “Anki - friendly, intelligent flashcards.” https://ankiweb.net/about, 2021.

[3] P. Supitayakul, Z. Yücel, A. Monden, P. Leelaprute, Investigation of the effects of audio-reinforcement on recollection rates of e-learning users (in preparation).