assessment and feedback
1. Vary Types of Writing over Time One writing assignment is never going to tell you everything about a learner's development. You require a variety of prompts over different time frames — and preferably, those should match realistic genres (emails, essays, stories, arguments, summaries, etc.). ThisRead more
1. Vary Types of Writing over Time
One writing assignment is never going to tell you everything about a learner’s development. You require a variety of prompts over different time frames — and preferably, those should match realistic genres (emails, essays, stories, arguments, summaries, etc.).
This enables you to monitor improvements in:
- Genre awareness: Are they able to change tone and structure between an academic essay and a personal email?
- Cohesion and coherence: Are their ideas becoming more coherent over time?
- Complexity and accuracy: Are they employing more advanced grammar and vocabulary without raising errors?
- Tip: Give similar or comparable tasks at important intervals (e.g., every few months), not only once at the end.
2. Portfolio-Based Assessment
One of the most natural and powerful means of gauging L2 writing development is portfolios. Here, students amass chosen writing over time, perhaps with reflections.
Portfolios enable you to:
- Monitor progress week by week, month by month, or even year by year.
- Make comparisons between early drafts and improved versions, stimulating metacognitive reflection.
- Invite students to reflect on what they have learned and what differed in their approach.
Why it works: It promotes ownership and makes learners more conscious of their own learning — not only what the teacher describes.
3. Holistic + Analytic Scoring Rubrics
Both are beneficial, but combined they provide a better picture:
- Holistic scoring provides a general impression of quality (such as band scores in IELTS).
- Analytic scoring divides writing into categories: content, organization, grammar, vocabulary, cohesion, etc.
- To measure change over time, analytic rubrics are more effective — they indicate whether grammar got better, even if content remained constant, or if structure got stronger.
Best practice: Apply the same rubric consistently over time to look for meaningful trends.
4. Make Peer and Self-Assessment a part of it
Language learning is social and reflective. Asking learners to review their own and each other’s writing using rubrics or guided questions can be potent. It promotes:
- Awareness of quality: They begin to notice characteristics of good writing.
- Growth mindset: They become able to view writing as something that can be developed.
- Metacognition: They reflect on their decisions, not only on what they got wrong.
Example: Ask, “What’s one thing you did better in this draft than in the last?” or “Where could you strengthen your argument?”
5. Monitor Fluency Measures Over Time
Occasionally, a bit of straightforward numerical information is useful. You can monitor:
- Word count per timed writing task
- Sentence length / complexity
- Lexical diversity (How many different words are they employing?)
- Error rates (mistakes per 100 words)
These statistics can’t tell the entire story, but they can offer objective measures of progress — or signal problems that need to be addressed.
6. Look at the Learner’s Context and Goals
Not every writing improvement appears the same. A business English student may need to emphasize clarity and brevity. A pupil who is about to write for academic purposes will need to emphasize argument and referencing.
Always match assessment to:
- Learner targets (e.g., IELTS pass, writing emails, academic essays)
- Instructional context (Are they intensively or informally learning?)
- First language influence (Certain structures may emerge later depending on L1)
7. Feedback that Feeds Forward
- Assessment isn’t scoring — it’s feedback for improvement. Comments should:
- Pinpoint trends (e.g., “You tend to drop article use — let’s work on that.”)
- Provide strategies, not corrections
- Prompt revision — the easiest indicator of writing growth is in how students can revise their own work
Example: “Your argument is clear, but try reorganizing the second paragraph to better support your main point.”
8. Integrate Quantitative and Qualitative Evidence
Lastly, keep in mind that writing development isn’t always a straight line. A student may try out more complicated structures and commit more mistakes — but that may be risk-taking and growth, rather than decline.
Make use of both:
- Quantitative information (rubric scores, error tallies, lexical range)
- Qualitative observations (student self-report, teacher commentary, revision history)
- Combined, these paint a richer, more human picture of writing development.
In Brief:
Strong approaches to measuring second-language writing progress over time are:
- With a range of writing assignments and genres
- Keeping portfolios with drafts and reflection
- Using consistent analytic rubrics
- Fostering self and peer evaluation
- Monitoring fluency, accuracy, and complexity measures
- Aligning with goals and context in assessment
- Providing actionable, formative feedback
- Blending numbers and narrative insight
The Timeless Problem with Learning Language Language learning is intimate, but traditional testing just can't manage that. Students are typically assessed by rigid, mass-produced methods: standardized testing, fill-in-the-blank, checklist-graded essays, etc. Feedback can be delayed for days, frequeRead more
The Timeless Problem with Learning Language
Language learning is intimate, but traditional testing just can’t manage that. Students are typically assessed by rigid, mass-produced methods: standardized testing, fill-in-the-blank, checklist-graded essays, etc. Feedback can be delayed for days, frequently in the form of generic comments like “Good job!” or “Elaborate on your points.” There’s little nuance. Little context. Little you engaged.
That’s where AI comes in—not to do the teachers’ job, but as a super-competent co-pilot.
AI/LLMs Change the Game
1. Measuring Adapted Skills
It’s not just feedback—it’s insight.
2. Personalized Feedback in Natural Language
Instead of “Incorrect. Try again,” an AI can say:
“‘You’re giving ‘advices’ as a plural, but ‘advice’ is an uncountable noun in English. You can say ‘some advice’ or ‘a piece of advice.’ Don’t worry—this is a super common error.'”
This kind of friendly, particular, and human feedback promotes confidence, not nervousness. It’s immediate. It’s friendly. And it makes learners feel seen.
3. Shifting to Level of Proficiency and Learning Style
AI systems are able to adjust the level and tone of their feedback to meet the learner’s level:
It also has the ability to understand how the individual learns best: visually, by example, by analogy, or by step-by-step instructions. Think of receiving feedback described in the mode of a story or in the way of colored correction, depending on your preference.
4. Multilingual Feedback and Translation Support
For multilingual students or ESL, AI can specify errors in the student’s home language, compare the structures of different languages, and even flag “false friends” (i.e., words that are the same but have different meanings in two languages).
5. Real-Time Conversational Practice
With the likes of voice input and chat interfaces, LLMs can practice real-life conversations:
And the best part? No judgment. You can make mistakes without blushing.
6. Content Generation for Assessment
Teachers or students may ask AI to create custom exercises based on a provided topic or difficulty level: teaching
Why This Matters: Personalized Learning Is Powerful Learning
Language learning is not a straight line. Others struggle with verb conjugation, others with pronunciation or cultural uses of language. Others get speech-tongue-tied, others are grammar sticklers who can’t write a wonderful sentence.
LLMs are able to identify such patterns, retain preferences (with permission), and customize not only feedback, but the entire learning process. Picture having a tutor who daily adjusts to your changing needs, is on call 24/7, never gets fatigued, and pumps you up each step of the way.
That’s the magic of customized AI.
Of Course, It’s Not Perfect
And let’s not forget the risk of students becoming too reliant on AI tools, instead of learning to think by themselves.
That’s why human teachers matter more than ever before. The optimal model is AI-assisted learning: teachers + AI, not teachers vs. AI.
What’s Next?
The future may bring:
Even writing partners who help you co-author tales and revise and explain along the way.
Final Thought
Personalized language assessment with LLMs isn’t a matter of time-saving or feedbackscaling—it’s a matter of giving the learner a sense of having been heard. Inspired. Empowered. When a student is informed, “I see what you’re attempting to say—here’s how to say it better,” that’s when real growth happens.
And if AI can make that experience more available, more equitable, and more inspiring for millions of learners across the globe—well, that’s a very good application of intelligence.
See less