Scribd
Upload
10 views

EdTech_assignment_1

The document outlines a conceptual model for an educational app focused on language learning, specifically vocabulary expansion through image recognition and translation. Users can upload images of household items to receive corresponding words and pronunciations in a foreign language, enhancing recall through visual connections. Performance is measured using spaced repetition techniques, with AI tools employed for image recognition and translation to create an interactive learning experience.

Uploaded by

邢泰然
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views

EdTech_assignment_1

The document outlines a conceptual model for an educational app focused on language learning, specifically vocabulary expansion through image recognition and translation. Users can upload images of household items to receive corresponding words and pronunciations in a foreign language, enhancing recall through visual connections. Performance is measured using spaced repetition techniques, with AI tools employed for image recognition and translation to create an interactive learning experience.

Uploaded by

邢泰然
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Educational Technologies – Conceptual Model and Interaction

Loop
Sjors Holtrop (s1646915) & Nikita Zelenskis (s2622157) & Nimish Pandey (s4022297) & Mehul Upase (s4017633)
Aaron Xing (s3644707) & Andrija Kuzmanov (s3766780) & Christina Irakleous (s3729664)

March 2024

1 Domain
Our domain is language learning. To be specific we focus on expanding the vocabulary and learning
new words in a foreign language. The primary problem our app addresses is that it can be boring to
memorize words in a different language. By creating a connection with items in your direct vicinity
it should be easier to recall and remember the item.
Vocabulary is the foundation of learning a language therefore the ability to recall a new word is
arguably the most important skill when learning a new language.

2 Use cases
The idea behind our application is to connect images/photos (input) and translate it to a word
(output) in the chosen language. Although a lot of applications already exist, images are a creative
and easy way to learn a language. Through the interface, the user could upload any image of a
household item they wish to memorize in a different language. Then, the user will get the generated
word on the screen as well as an audio output to hear the pronunciation. Through this process,
individuals not only will be able to improve skills such as pronunciation, but also be able to recall a
word easily because of the connection with the item.
After enough pictures have been taken, the user can start practicing with flashcards. After practicing
with the flashcards the user will get feedback of how many words they have memorized.

3 Measuring performance
For measuring performance, we can use the same techniques that well-established spaced repetition
system (SRS) learning tools use. Learners self-report how difficult it was to recall a certain word,
picking between the categories: Wrong, Hard, Ok, and Easy. This also affects how often a word will be
scheduled for review. The learner’s performance is based on how many words have progressed from
Wrong/Hard to Ok/Easy, indicating the word is committed to long-term memory. If learners do not
progress, i.e., a word is Wrong multiple times in a row, the application asks them to take a new, more
memorable picture.
If the learner repeats mistaking certain objects in the pictures, the software can prompt some hints
to enhance the connection between the images and the word, like similarly spelled words (sharing the
same base), or words of related meanings, which the user has already grasped.

4 Conceptual tooling
For our project, we will use four key conceptual tools. Firstly, we will create an interface for taking
and uploading images. Secondly, we will use AI for image/object recognition. We want to be able to
recognize the key object in the image. For this task, something like Google’s Cloud Vision API can
be used. Furthermore, AI will also be used to translate the word into the desired language. Here the
DeepL API offers great translation capabilities for most of the widely spoken languages.
Finally, we want to make this an interactive learning experience, which is why we can use rein-
forcement learning to help us pick the best words to show to the user. That way, our application can
adjust to different learning rates.

You might also like