AUVANA: An Automated Video Analysis Tool for Visual Complexity

Alghamdi, Emad A.; Velloso, Eduardo; Gruba, Paul

doi:10.31219/osf.io/kj9hx

Cited by 7 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current study extends our previous work in which we examined the relative contribution of linguistic complexity (Alghamdi et al, in press, 2022) and visual complexity (Alghamdi et al, 2021) on estimating instructional video difficulty by investigating the impact of using multimodal complexity features to predict video difficulty in two video genres: academic lectures (AL) and government advertisement (GA) video clips. Furthermore, the current study investigates which ensemble machine learning approaches are more predictive of intermediate English language learners' judgment of video difficulty in AL, GA, and in both video genres combined (All).…”

Section: Aim Of the Studymentioning

confidence: 54%

See 1 more Smart Citation

Leveraging ensemble machine learning and multimodal video complexity for better prediction of video difficulty in second language

Alghamdi¹

2022

Preprint

View full text Add to dashboard Cite

Research into multimodal language learning has shown that video materials are engaging and effective in teaching and learning language skills. While previous studies have predominantly focused on how to make learning from video more effective, little research has been directed at estimating video content difficulty. This study, therefore, aims to examine the efficacy of developing predictive models using different configurations of ensemble machine learning approaches (averaging, bagging, boosting, and stacking) and video complexity features (acoustic, phonological, lexical, syntactic, and visual complexity features). A corpus of 640 videos that were subjectively rated for content difficulty by 322 English language learners was used to build and evaluate predictive models. The results demonstrated that ensemble machine learning models substantially outperformed baseline regression models in predicting video difficulty. The findings are discussed in terms of their applications in second language learning and assessment.

show abstract

Section: Aim Of the Studymentioning

confidence: 54%

“…In this study, I used previously extracted verbal complexity features (Alghamdi et al, in press, 2022) and visual complexity features (Alghamdi et al, 2021) to create our set of multimodal video complexity features. In total, the set contains 390 multimodal complexity features.…”

Section: Multimdoal Complexity Featuresmentioning

confidence: 99%

Leveraging ensemble machine learning and multimodal video complexity for better prediction of video difficulty in second language

Alghamdi¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To cater to proficiency levels, researchers have relied on traditional lexical complexity measures to classify readers and listening texts (see Révész & Brunfaut, 2013), and recent innovations are exploring video texts used for listening comprehension. In fact, Alghamdi et al (2021) created AUVANA, a crossplatform to measure video complexity. Perhaps until those technologies become more accessible to the regular language teacher, a way forward for teachers could possibly be to follow "the grade the task not the (multimodal) input" principle, to ensure that learners are exposed to a range of MMI.…”

Section: Discussionmentioning

confidence: 99%

Teachers’ voices on multimodal input for second or foreign language learning

Cárdenas-Claros,

Sydorenko,

Huntley

et al. 2023

Language Teaching Research

View full text Add to dashboard Cite

Multimodal input – which combines written, auditory, and/or visual modalities – is pervasive in everyday life and could serve as a source of rich input in language teaching. In recent years, research has determined that vocabulary learning is one of the clear benefits of being exposed to such input. Regrettably, only a handful of studies have investigated whether and how second language (L2) teachers approach multimodal input in teaching. To further contribute to the research–practice dialogue, we examined factors that influence L2 teachers’ use of multimodal input in L2 teaching. This qualitative case study presents an in-depth analysis of interview data derived from 21 practitioners in various L2 teaching contexts globally. Following three rounds of data analysis, 24 factors were identified and are presented in four themes. The results indicate that teachers: (1) paid close attention to their students’ needs and goals; (2) drew on their own learning and teaching experiences and training supported by research-based practices; (3) relied on sound pedagogical principles; and (4) faced a number of contextual challenges relevant to their curricula and teaching contexts.

show abstract

“…For the purposes of our larger research agenda, we built a corpus of 640 videos in a corpus named Second Language Videotext Complexity (SLVC; Alghamdi et al, 2021). In the present study, we made use of only 320 videotexts from this corpus that deploy different instructional designs, as per typologies of video lecture instructional design provided by Crook & Schofield (2017).…”

Section: Methodsmentioning

confidence: 99%

“…As we pursue an overall agenda, we will continue to conduct research in three areas: First, we plan to evaluate the generalizability of our linguistic complexity feature set on other genres of videotext, for example, government advertisements, television shows, and movies. Second, we plan to investigate the relation of visual complexity to instructional video design as a predictor of video lecture difficulty using visual complexity tools such as (AUVANA; Alghamdi et al, 2021). Finally, we will incorporate both linguistic and visual complexity features in an automated web tool for assessing video lecture difficulty and evaluate its utility in pedagogical activities.…”

Section: Limitations and Future Workmentioning

confidence: 99%

The Relative Contribution of Language Complexity to Second Language Video Lectures Difficulty Assessment

Alghamdi

Gruba

Velloso

2022

The Modern Language Journal

Self Cite

View full text Add to dashboard Cite

Although core in the teaching of academic language skills, little research to date has investigated what makes video-recorded lectures difficult for language learners. As part of a larger program to develop automated videotext complexity measures, this study reports on selected dimensions of linguistic complexity to understand how they contribute to overall videotext difficulty. Based on the ratings of English language learners of 320 video lectures, we built regression models to predict subjective estimates of video lecture difficulty. The results of our analysis demonstrate that a 4-component partial least square regression model explains 52% of the variance in video difficulty and significantly outperformed a baseline model in predicting the difficulty of videos in an out-of-sample testing set. The results of our study point to the use of linguistic complexity features for predicting overall videotext difficulty and raise the possibility of developing automated systems for measuring video difficulty, akin to those already available for estimating the readability of written materials.

show abstract

AUVANA: An Automated Video Analysis Tool for Visual Complexity

Cited by 7 publications

References 44 publications

Leveraging ensemble machine learning and multimodal video complexity for better prediction of video difficulty in second language

Leveraging ensemble machine learning and multimodal video complexity for better prediction of video difficulty in second language

Teachers’ voices on multimodal input for second or foreign language learning

The Relative Contribution of Language Complexity to Second Language Video Lectures Difficulty Assessment

Contact Info

Product

Resources

About