Using KidLogger for scientific research

Since 2001, KidLogger is contributing into the global Surveillance Economy as a tiny freeware keylogger that also collected other user activity on the computer in a chronological order. Later in 2010 KidLogger online parental control beta was released to allow parents to supervise children's smartphones. In 2016 KidLogger technology start being used by Academia community to collect data-sets for machine learning experiments.

Scientists around the world used KidLogger application to research on humans psychometric modeling using digital data traces which are produced by computer usage. The major challenges are to detect how some temporal activity metrics are correlated with certain Big Five personality metrics (FFM) that has been defined as 'openness to experience', conscientiousness, extraversion, agreeableness, and neuroticism (often represented by the acronyms OCEAN or CANOE). Also determining various effects on multitasking work in computer environment and its correlation with stress represents the big area of research. The negative influence of social media on a students' mood as a distraction factor is also among the biggest findings by the researchers, which means that further investigation into social media usage should be made in the future. In other hands measuring digital traces allows finding the influence of other factors into information workers such as amount of sleep, physiological or cognitive reasons, offsite motivation;
The scientific community also works to discover effective collection methods and better measure of information about the use of the computer applications by the user for later studying the patterns of the user's behavior. Various industries are also highly interested in developing a measurement model for human factors decisions and privileged user behavior in critical information infrastructures that helps in computer forensics and security. In the educational environment there were attempts to monitor computer traces to find gaps in learning processes to establish professional ethics for translators;

KidLogger application allows collecting various traces of user activity and events on computer or mobile devices. The list of data features includes:

  • Start and end time of computer usage since Computer or Smartphone startup;
  • Programs usage time, switch time;
  • Window title activation time;
  • Input idle start, stop and duration time;
  • Website usage, switch and activation time;
  • Mouse movements and clicks;
  • Keyboard typing events, with active application or website name;
  • Communication data: Skype in / Out messages;
  • Web Browser plugin with in-depth web page activity traces: scroll, click, hover navigation, UI response wait time;
  • Eye tracking data (with IR camera, Windows 10 only);
  • Periodic display screenshot capture;
  • Periodic web-camera photo capture;
  • Microphone sound recording to detect voice communication activity;

KidLogger allows producing data in CSV, JSON, HTML formats with millisecond-precision format;

Target Group studies with KidLogger is possible with On-Premise KidLogger Cloud that allows to collect and analyze data across school or university scope. Please contact us for more information.

How to set up KidLogger for dataset collection

It is very easy to collect a dataset with KidLogger application on Windows, Mac, Linux, Android. KidLogger options allows selecting which features you need to include into dataset collection.

Install KidLogger Application, open and Options ( Define Format options. Define millisecond time format and granularity vs aggregation.

By default, KidLogger application does not require connecting with cloud service, and it is possible to conduct monitoring and store data locally on the computer.

How to collect data from CSV or JSON file

KidLogger allows to output collected dataset into CSV or JSON file for later processing. The dataset includes date and time of event, type, name, title, duration and attribute.


Mouse events, 'mouse' tag:
mouse,13:24:00:526,notepad, Move, 1437:945
mouse,13:24:00:558,notepad, Move, 1354:849
mouse,13:24:00:590,notepad, Move, 1313:806
mouse,13:24:00:621,notepad, Move, 1295:776
mouse,13:24:00:646,notepad, Move, 1278:738

mouse,11:08:53:474,notepad, Scroll ,689:728
mouse,11:16:23:698,notepad, Click ,144:30

where 'notepad' is currently active process name.

Keyboards events, 'keystroke' tag:


Current UI application selection, 'app' tag:

app,13:25:47:854,notepad, Untitled - Notepad

KidLogger is currently the application currently selected by user with 'Untitled - Notepad' window caption (title).

Current Web site URL selection, 'URL' tag:

url,11:16:23:625,0,,Incomming (96) - - Gmail - Google Chrome

Other tags: system, folder, mp3, idle, jpg, chat


On-Premise KidLogger Cloud

Allows collecting data into a central location across multiple devices located over the School or organization departments;

Combines data for a single personality across multiple devices like phones and computers and integrate them into a single journal record. This simplifies to perform multi-device context studies.

Data export: SQL tables with traces data.

Open-Source monitoring tool

We are always open for collaboration with educational organizations and ready to provide the latest source code of KidLogger applications, Cloud Server and support research with our experimental custom features.


List of references where KidLogger was used:

This list will help you to better define the scope and achievements
of past researches. The list of researches and studies conducted in the field:


Detecting Multitasking Work and Negative Routines from Computer Logs


Strictly by the Facebook: Unobtrusive Method for Differentiating Users


Digital footprints: predicting personality from temporal patterns of technology use


Stress and multitasking in everyday college life: an empirical study of online activity


Sleep Debt in Student Life: Online Attention Focus, Facebook, and Mood


Development of an Application for Mobile Devices to Record Learner Interactions with Web-Based Learning Objects



Collecte, traitement et analyse de traces pour identifier la circulation de pratiques numériques des lycéens


Workstation Analytics in Distributed Warfighting Experimentation


More friends, more interactions? The association between network size and interactions on Facebook



Gisela Marcelo Wirtnizer José Jorge Amigo Extremera

Exploring mobile device usage patterns by using the FANN neural network library