ARLang: An Outdoor Augmented Reality Application for Portuguese Vocabulary Learning

TL;DR

A proof-of-concept system that displays bilingual text and sound labels on physical objects outdoors using augmented reality for foreign vocabulary learning, and results indicate that participants preferred learning with virtual labels on real-world objects outdoors over learning with flashcards.

Abstract

With recent computer vision techniques and user-generated content, we can augment the physical world with metadata that describes attributes, such as names, geo-locations, and visual features of physical objects. To assess the benefits of these potentially ubiquitous labels for foreign vocabulary learning, we built a proof-of-concept system that displays bilingual text and sound labels on physical objects outdoors using augmented reality. Established tools for language learning have focused on effective content delivery methods such as books and flashcards. However, recent research and consumer learning tools have begun to focus on how learning can become more mobile, ubiquitous, and desirable. To test whether our system supports vocabulary learning, we conducted a preliminary between-subjects (N=44) study. Our results indicate that participants preferred learning with virtual labels on real-world objects outdoors over learning with flashcards. Our findings motivate further investigation into mobile AR-based learning systems in outdoor settings.

Figures (6)

• Figure 1: (a) Left: Unplayed AR tag on top of a barbecue grill displaying "Churrasqueira", the noun in Portuguese, and "Barbecue Grill", the English translation. Right: The green border around the noun in Portuguese indicates the tag was played. Figure \ref{['fig:ankiapp']} shows the same content as a flashcard. (b) Left: Buttons on the screen's bottom-right corner load and unload the AR tags. Right: Buttons on the screen's bottom-right corner fold after loading AR tags. (c) On the top edge of the screen, the slider is used to adjust AR tag rotation. The counter of played tags is shown below the slider.
• Figure 2: Left: Front face of a flashcard with Portuguese written noun, Portuguese pronunciation audio, and image of a barbecue grill. Right: Back face of the same flashcard with Portuguese written noun, Portuguese pronunciation audio, an image of a barbecue grill, English translation, and difficulty scale. Figure \ref{['fig:artag']} shows the same content as an AR tag.
• Figure 3: View of the outdoor ARLang study area showing pedestrian sidewalks, seating spaces, and campus buildings.
• Figure 4: Bird's-eye view of the location where the ARLang group conducted the user study. The orange border bounds the approximate study area and the green line marks the walking path along which AR objects are labeled, starting at point A.
• Figure 5: (a) Mean Overall Scores of each experimental group with their $95\%$ confidence interval. (b) Mean Pt-En Scores of each experimental group with their $95\%$ confidence interval. (c) Mean En-Pt Scores of each experimental group with their $95\%$ confidence interval.