Automated report writing

I have never met a teacher who enjoys writing reports. If you have one or two small groups, it’s not too bad, but if you have ten different groups of thirty kids, crunching out 300 reports is a bind. And, often, a pressured bind at that, shoehorned between exam results and end of term. But with any luck, a new breed of software could spell the end of such drudgery.

Do robot writers sweat over deadlines?That’s right: software now exists that can take data, such as sports results, and generate reports from it. What surprises me is that the reports are readable, and not obviously computer-generated. Take, for example, this extract of a report of a football game:

The Badgers scored 20 points in the first quarter on a Russell Wilson touchdown pass, a Montee Ball touchdown run and a James White touchdown run.

I have no idea what it all means, but it’s more reader-friendly than a table of results. That’s from a company called Narrative Science, as reported in Computer-generated journalism: A new kind of automatic writing. That article also states that other types of data can be used, such as financial reports, real estate information, election and polling data. So the obvious question is, why not pupil’s data too?

Here’s another example, this time from a project called StatsMonkey, as reported in Automated Sports Reporters Coming This Summer:

An outstanding effort by Willie Argo carried the Illini to an 11-5 victory over the Nittany Lions on Saturday at Medlar Field.

Note that the report is not, as you might expect, as dry as dust. I know the inclusion of the word “outstanding” would not qualify it for the Pulitzer Prize, but you have to congratulate the programmers for making that possible.

So we have some big questions here. First, is automated writing for end-of-term reports ethical? Personally, I think it is. Even if you write your reports by hand, you will still have a number of stock phrases you apply in each one – and after a while, it shows, because it’s hard to write 30 different variations of the same observation. Arguably, this sort of software (Narrative Science) is better because it doesn’t simply take the data and insert it into a template. Besides, teachers have been using technology to make their report writing easier for years, even if all it involves is selecting phrases from a sentence bank by pointing and clicking. In fact, while information management system software was still in its infancy I put together a mail-merge system which topped and tailed each report with the pupil’s name and group, the option they were taking, their grades and their teacher’s name, which radically cut down on the amount of time needed for writing the reports.

Second, how would you ensure that the reports created in this way were good enough? I think the new approach would have to be tested on a small group while still keeping the current system in place. The teacher would have to be able to edit the reports, or replace them, if the main points were not brought out, or brought out strongly enough.

Third, would it be acceptable to parents? You would need to involve them in the pilot study, but it would also be instructive to ask some parents to volunteer for a scientific experiment, in which they would receive a report but not be told whether it had been computer-generated or not. If they couldn’t tell the difference, why would they mind, as long as they felt confident that the data and the conclusions derived from it were correct? You never know, some parents might even find the automated reports more informative and easier to read!

The benefits in terms of teachers’ time, and therefore the opportunity cost in terms of what they could be doing instead of writing hundreds of reports, are potentially enormous. And the same technology could be applied to reports to Governors, project progress reports, possibly even lesson observations. You could use it to produce readable overall reports for each subject or year group.

From a broader perspective, should sports and other journalists be quaking in their boots and scanning the job centre postings? I think not. This automated reporting is fine for crunching data and making it palatable, but to make a report come alive still requires a human being.

I cannot, for instance, imagine a machine producing something like this:

[George] Best had come in along the goal line from the corner-flag in a blur of intricate deception. Having briskly embarrassed three or four challengers, he drove the ball high into the net with a fierce simplicity that made spectators wonder if the acuteness of the angle had been an optical illusion.

“What was the time of that goal?” asked a young reporter in the Manchester United press box. “Never mind the time, son,” said an older voice beside him. “Just write down the date.”


It was the kind of wind that seemed to peel the flesh off your bones and come back for the marrow.

Or this description of boxer Joe Bugner:

The physique of a Greek statue but fewer moves.

Each of those quotes are from the pen of Hugh McIlvanney, as reported in Hugh McIlvanney remains the matchless Master.

The writer of that article, Norman Giller, tells us:

To watch McIlvanney at work is not a pretty sight. He carves slowly like Leonardo, chiselling out every word with care and consideration…. His words are his currency and he will not relax until every dot and comma is accounted for. Hughie cannot write anything without total commitment; even a note to the milkman produces the agony of creation.

Somehow, I can’t see anyone describing a robot reporter in such terms!