Introduction

OpenLA is “Open-source library for e-Book Log Analysis”.

This Python library helps to reduce redundant development of preprocessing e-book log: calculating reading time of each learner, counting up operations, page-wise summary of students behavior, etc.

API concept

For analyzing e-Book log, four types of preprocessing (getting course information, converting the log into a form suitable for analysis, extracting the required information, and visualizing the data) are essential and common in various analysis. To reduce the reinvention of these common processing, OpenLA provides corresponding four types of modules: Course Information, Data Conversion, Data Extraction, and Data Visualization module.

Course Information Module

• Course Information Module Document

• Tutorial of Course Information Module

Data Conversion Module

• Data Conversion Module Document

• Tutorial of Data Conversion Module

Data Extraction Module

• Data Extraction Module Document

• Tutorial of Data Extraction Module

Data Visualization Module

• Data Visualization Module Document

Installation

OpenLA is registered to PyPi (https://pypi.org/project/OpenLA/). You can install by pip command.

pip install OpenLA

Dataset for OpenLA

The dataset used in this library has the same structure with that of the open source ones used to conduct Data Challenge Workshops in LAK19 and LAK20 ( https://sites.google.com/view/lak20datachallenge ).

The dataset includes four types of files.

Course_#_EventStream.csv

Data of the logged activity data from learners’ interactions with the BookRoll system.

Columns: ‘userid’, ‘contentsid’, ‘operationname’, ‘pageno’, ‘marker’, ‘memo_length’, ‘devicecode’, and ‘eventtime’

Course_#_LectureMaterial.csv

Information about the length of the lecture materials used

Columns: ‘lecture’, ‘contentsid’, and ‘pages’

Course_#_LectureTIme.csv

Information about the schedule of the lectures.

Columns: ‘lecture’, ‘starttime’, and ‘endtime’

Course_#_QuizScore.csv

Data on the final score for each student.

Columns: ‘userid’ and ‘score’

From ver. 0.2.1, OpenLA can treat grade point data which does not exist in LAK19 and LAK20 dataset.

Course_#_GradePoint.csv

Data on the final grade for each student.

Columns: ‘userid’ and ‘grade’

# is a course id. BookRoll is an e-Book system to record learning activities.

As an alternative to CSV files, pandas DataFrames can also be loaded.

If you need sample dataset, please contact with openla@limu.ait.kyushu-u.ac.jp .

For more information about BookRoll and the learning analytics platform on which the data was collected, please refer to the following:

• Brendan Flanagan, Hiroaki Ogata, Integration of Learning Analytics Research and Production Systems While Protecting Privacy, Proceedings of the 25th International Conference on Computers in Education (ICCE2017), pp.333-338, 2017.

• Hiroaki Ogata, Misato Oi, Kousuke Mohri, Fumiya Okubo, Atsushi Shimada, Masanori Yamada, Jingyun Wang, and Sachio Hirokawa, Learning Analytics for E-Book-Based Educational Big Data in Higher Education, In Smart Sensors at the IoT Frontier, pp.327-350, Springer, Cham, 2017.