Actionable companion · Learning design & outcomes

Learning with agency: An Al-BERT-Bi-GRU-LDA algorithm for negative sentiment analysis on Bilibili comments

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paper Search paper agent CC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Secondary school, Adult & professional learning. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

The number of online self-learning users has been increasing due to the promotion of various lifelong learning programs. Unstructured commentary text related to their real learning experience regarding the learning process is generally published by users to show their opinions and complaints. The article aims to utilize the dataset of real text comments of 10 high school mathematics courses participated by high school students in the Bilibili platform and construct a hybrid algorithm called the Artificial Intelligence-Bidirectional Encoder Representations from Transformers (BERT) + Bidirectional Gated Recurrent Unit (BiGRU) and linear discriminant analysis (LDA) to crunch data and extract their sentiments. A series of tests regarding algorithm comparison were conducted on the educational review datasets. Comparative analysis found that the proposed algorithm achieves higher precision and lower loss rates than other alternative algorithms. Meanwhile, the loss ratio of the proposed algorithm was kept at a low level. At the topic mining level, the topic clustering of negative comments found that the barrage content was very messy and the complexity of the course content was generally reported by the students. Some problems related to videos were also mentioned. The outcomes are promising that the fundamental issues underlined by the students can be effectively resolved to improve curriculum and teaching quality.

What kind of evidence is this?

Supporting AI learning science · Design requires full-text appraisal

Stage: Secondary school; Adult & professional learning. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

Moreover, some students reported that more than the video content was needed and hoped to increase the range. Students have less negative feedback about teachers regarding teacher attributes since high teaching quality is available in online courses. Participants also reported that the order of the courses needed to be corrected. Regarding resource acquisition, a few students noted that courseware and handouts could not be downloaded because links expired.

Limitations and uncertainty · source passage

The remainder of the article is organized as follows: Section ‘Related Works’ provides a literature review of sentiment analysis and its applications in education. Section ‘The Proposed Algorithm: ABGAL’ introduces the Al-BERT-BiGRU+LDA algorithm based on the attention mechanism. Section ‘Experimentation’ presents the experimental dataset and experimental results. Section ‘Conclusion’ concludes the research and presents a direction for future research.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.

A 90-day district pilot

Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
Days 16–30 · Design. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. Name an accountable owner and set the baseline, success threshold and budget before implementation.
Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
Days 61–90 · Decide. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Ziyu Liang; Jun Chen. An Al-BERT-Bi-GRU-LDA algorithm for negative sentiment analysis on Bilibili comments. PeerJ Computer Science (2024-05-15). https://doi.org/10.7717/peerj-cs.2029

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.