• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Applying IRT Technique for Question Difficulty Estimation in Various Mind Quiz Games Modes

Student: Mishalkin Ivan

Supervisor: Alexander Sirotkin

Faculty: St. Petersburg School of Physics, Mathematics, and Computer Science

Educational Programme: Big Data Analysis for Business, Economy, and Society (Master)

Year of Graduation: 2020

In 2020 lots of things moved online. The popular in CIS area mind quiz game What? Where? When? went online this year along with the online version. The new format caused new possibilities to cheat, e.g., searching on the internet. In this work, we upgraded the framework designed for cheating detection. Like the base model, the current one is based on the Item Response Theory (IRT). We estimate latent variables like players' skills, questions' difficulty, and team preference to online games with Stochastic Gradient Descent(SGD). The model gives a good ROC AUC of 0.8. However, the model has some limitations. It also performs much better with rich data, i.e. the teams participated in many tournaments of both modes, each tournament had lots of teams.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses