AI-assisted analysis of content, structure, and sentiment in MOOC discussion forums

被引:3
作者
Yee, Michael [1 ]
Roy, Anindya [2 ]
Perdue, Meghan [2 ]
Cuevas, Consuelo [1 ]
Quigley, Keegan [1 ]
Bell, Ana [3 ]
Rungta, Ahaan [2 ]
Miyagawa, Shigeru [4 ]
机构
[1] MIT Lincoln Lab, Artificial Intelligence Technol Grp, Lexington, MA 02421 USA
[2] MIT, Open Learning, Cambridge, MA USA
[3] MIT, Dept Elect Engn & Comp Sci, Cambridge, MA USA
[4] MIT, Dept Linguist & Philosophy, Cambridge, MA USA
关键词
MOOCs; discussion forums; forum posts; natural language processing; text classification; machine learning; transformers; artificial intelligence;
D O I
10.3389/feduc.2023.1250846
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
Discussion forums are a key component of online learning platforms, allowing learners to ask for help, provide help to others, and connect with others in the learning community. Analyzing patterns of forum usage and their association with course outcomes can provide valuable insight into how learners actually use discussion forums, and suggest strategies for shaping forum dynamics to improve learner experiences and outcomes. However, the fine-grained coding of forum posts required for this kind of analysis is a manually intensive process that can be challenging for large datasets, e.g., those that result from popular MOOCs. To address this issue, we propose an AI-assisted labeling process that uses advanced natural language processing techniques to train machine learning models capable of labeling a large dataset while minimizing human annotation effort. We fine-tune pretrained transformer-based deep learning models on category, structure, and emotion classification tasks. The transformer-based models outperform a more traditional baseline that uses support vector machines and a bag-of-words input representation. The transformer-based models also perform better when we augment the input features for an individual post with additional context from the post's thread (e.g., the thread title). We validate model quality through a combination of internal performance metrics, human auditing, and common-sense checks. For our Python MOOC dataset, we find that annotating approximately 1% of the forum posts achieves performance levels that are reliable for downstream analysis. Using labels from the validated AI models, we investigate the association of learner and course attributes with thread resolution and various forms of forum participation. We find significant differences in how learners of different age groups, gender, and course outcome status ask for help, provide help, and make posts with emotional (positive or negative) sentiment.
引用
收藏
页数:17
相关论文
共 72 条
[1]  
Agrawal AkshayVenkatraman., 2015, YouEDU: addressing confusion in MOOC discussion forums by recommending instructional video clips
[2]   Automatic content analysis of asynchronous discussion forum transcripts: A systematic literature review [J].
Ahmad, Mubarik ;
Junus, Kasiyah ;
Santoso, Harry Budi .
EDUCATION AND INFORMATION TECHNOLOGIES, 2022, 27 (08) :11355-11410
[3]   Systematic Review of Discussion Forums in Massive Open Online Courses (MOOCs) [J].
Almatrafi, Omaima ;
Johri, Aditya .
IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 2019, 12 (03) :413-428
[4]   A Multidimensional Deep Learner Model of Urgent Instructor Intervention Need in MOOC Forum Posts [J].
Alrajhi, Laila ;
Alharbi, Khulood ;
Cristea, Alexandra, I .
INTELLIGENT TUTORING SYSTEMS (ITS 2020), 2020, 12149 :226-236
[5]  
[Anonymous], 2015, P 2 2015 ACM C LEARN, DOI DOI 10.1145/2724660.2724677
[6]   Towards Cross-domain MOOC Forum Post Classification [J].
Bakharia, Aneesha .
PROCEEDINGS OF THE THIRD (2016) ACM CONFERENCE ON LEARNING @ SCALE (L@S 2016), 2016, :253-256
[7]  
Barbieri F., 2020, Proceedings of Findings of EMNLP
[8]  
Bo Pang, 2008, Foundations and Trends in Information Retrieval, V2, P1, DOI 10.1561/1500000001
[9]   Dynamics of MOOC Discussion Forums [J].
Boroujeni, Mina Shirvani ;
Hecking, Tobias ;
Hoppe, H. Ulrich ;
Dillenbourg, Pierre .
SEVENTH INTERNATIONAL LEARNING ANALYTICS & KNOWLEDGE CONFERENCE (LAK'17), 2017, :128-137
[10]   Learning about Social Learning in MOOCs: From Statistical Analysis to Generative Model [J].
Brinton, Christopher G. ;
Chiang, Mung ;
Jain, Shaili ;
Lam, Henry ;
Liu, Zhenming ;
Wong, Felix Ming Fai .
IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 2014, 7 (04) :346-359