Brands over time

Fuse Energy
over time

Every year keeps its colour across every chart.│ ChatGPT, 30 Nov 2022

232 of Fuse Energy's own blog posts, press releases and announcements, 2026 to 2026, measured sentence by sentence. How the writing has moved over the years, how it compares with 11 other energy suppliers, and what it sounds like in its own words.

Pages measured
232
Years covered
2026–26
Archived before ChatGPT
0
Blog · press
132 · 100

01 · Homepage

One capture a year

Fuse Energy's homepage from 2023 to 2023, closest to 1 July, from the Internet Archive. Pick a year or press play. Each headline is quoted from its capture and links to the archived copy.

2023fuseenergy.com19 Jul 2023
Fuse Energy homepage, 19 Jul 2023

Screenshot of Fuse Energy’s homepage (fuseenergy.com) as archived by the Internet Archive on 19 Jul 2023. © Fuse Energy or its licensors. Shown for comparison and review; not endorsed by Fuse Energy.

Homepage

2023

No headline in this capture

Page title

Fuse · Home

Open on the Internet Archive

1 captures. Screenshots are rendered from the archive and can pull in images archived later than the page itself; dates come from the capture. Years without a capture are greyed out in the strip.

02 · Measures by year

How the writing moved

Every year’s pages, averaged. Pick a measure. Hatched bars rest on fewer than 10 pages: context, not a finding. The page count sits under each year.

Sentence lengthAverage words per sentence.
5
10
15
Energy avg 14.8
14.2
ChatGPT · Nov 2022
2015no pages
2016no pages
2017no pages
2018no pages
2019no pages
2020no pages
2021no pages
2022no pages
2023no pages
2024no pages
2025no pages
2026100 pp
10 or more pagesFewer than 10 pages: context, not a findingSector averageChatGPT released
Show as a table
YearSentence lengthPages
202614.2100

Years with pages: 2026 (100). Dates come from page metadata, structured data, the URL, or the month a page was first archived (a latest possible date).

03 · Against its sector

Fuse Energy among energy suppliers

Each dot is one brand’s mean across all its measured pages; the tick is the sector average. Only brands with 10 or more measured pages are shown or counted. Select a dot to open that brand.

  1. Em dashes

    95% less than its sector

    0.15 against a sector average of 2.96; lowest of 11.

  2. "We"

    68% less than its sector

    14% against a sector average of 42%; lowest of 11.

  3. "You"

    67% more than its sector

    85% against a sector average of 51%; highest of 11.

Sentence lengthMid-table, 7th of 11
Fuse Energy 14.3
13.316.4
ContractionsLowest of 11
Fuse Energy 8.0
8.024.4
"You"Highest of 11
Fuse Energy 85%
28%85%
"We"Lowest of 11
Fuse Energy 14%
14%65%
QuestionsLowest of 11
Fuse Energy 1.7
1.77.1
Long wordsHighest of 11
Fuse Energy 32%
19%32%
Em dashesLowest of 11
Fuse Energy 0.15
0.157.68
AI-associated wordsHighest of 11
Fuse Energy 2.62
0.552.62
ExclamationsLowest of 11
Fuse Energy 0.00
0.001.86
Page length2nd highest of 11
Fuse Energy 1,458
6681,774

Pages measured: ScottishPower 220 · Utilita 70 · Good Energy 290 · Ecotricity 27 · Outfox the Market 0 · Fuse Energy 232 · Octopus Energy 289 · British Gas 199 · EDF 280 · OVO 157 · E.ON Next 132 · So Energy 53. Measures and method: SGR-010; the brand list and sectors come from SGR-009.

04 · Vocabulary

Words Fuse Energy uses more than its peers

The words this brand reaches for more often than the rest of its sector. This is subject matter more than voice.

understanding30.6 vs 2.9
homeowners20.4 vs 1.8
uk's21.2 vs 2.2
reliance19.4 vs 1.5
mission19.5 vs 2.0
financial26.0 vs 4.9
crucial17.1 vs 1.1
abundant19.4 vs 0.5
significant23.9 vs 4.7
usage31.4 vs 8.4
responsible16.4 vs 1.6
infrastructure22.9 vs 4.8
Fuse EnergySector peers

Uses per 10,000 words, ranked by weighted log-odds (Monroe et al. 2008) across 232 pages. Product names and page furniture filtered automatically; list not yet reviewed.

05 · In its own words

What it sounded like

Openings of real pages, quoted word for word, oldest first. Each links to the page, or to the Internet Archive’s copy when it has gone.

20265 Jun · Blog
“Choosing a solar panel installer is a significant decision for any UK homeowner looking to invest in renewable energy. The quality of your installation directly impacts your system's long-term performance, safety, and financial returns. This guide will walk you through the essential steps to select a reliable and accredited installer, ensuring your solar panels deliver maximum value for years to come.”
How to choose a solar panel installer
202630 Aug · Blog
“Installing a heat pump in Chelsea's distinctive housing stock, often characterised by Victorian terraces and conservation area properties, presents both unique considerations and significant opportunities for homeowners. Beyond the immediate benefits of efficient heating, a heat pump can enhance property value and align with modern energy demands in this premium London borough.”
Heat pumps in Chelsea: efficiency and value

06 · Every page

All 232 pages, by year

The full list behind every number above, with links to the live page or the archived copy. 232 count towards the measures. Pages with no reliable date count in the overall numbers but in no year.

2026100 pages
In the overall numbers, no year132 pages

07 · Method

How this was measured

The pages

Fuse Energy's own blog posts, press releases and announcements, fetched from the live site in 2026 and from the Internet Archive for 2015 to November 2022. Homepages are shown as captures; product and help pages are not measured.

The measures

Code counts from ScriptGrain’s writing instruments: sentence length and rhythm, contractions, pronouns, punctuation, long words, and three published lists of AI-associated words. No AI model reads or judges any page.

What it cannot say

These measures describe style. They cannot tell who or what wrote a page, and nothing here says or implies that any brand used AI to write.

Sample sizes

Every number carries its page count. Years under 10 pages, and before-and-after comparisons with under 10 pages on a side, are shown as context only.

Sentence length
Average words per sentence.
Sentence rhythm
How much sentence length varies (standard deviation over mean). Higher reads less even.
Contractions
Contractions (we're, you'll, it's) per 1,000 words. A rough gauge of how conversational the writing is.
"You"
Share of I/we/you pronouns that are "you": how much the writing addresses the reader.
"We"
Share of I/we/you pronouns that are "we": how much the writing talks about the organisation.
Questions
Question marks per 1,000 words.
Exclamations
Exclamation marks per 1,000 words.
Long words
Share of words with seven or more letters.
Em dashes
Em dashes per 1,000 words.
AI-associated words
Words from SGR-007's three AI-associated lists, per 1,000 words. These are style markers that people used long before ChatGPT; a higher rate says nothing about who or what wrote the page.
AI-era marketing words
Marketing words that became more common in AI-era copy (seamless, elevate, unlock...), per 1,000 words. A style measure only.
Quieter LLM-favoured words
Everyday words language models are known to over-use, per 1,000 words. A style measure only.
AI-associated sentence shapes
Sentence patterns such as "not just X, but Y", found by ScriptGrain's cliche checker, per 1,000 words. A style measure only.
Page length
Average words per page.

Studies: SGR-009: Do brands in the same sector sound the same? · SGR-010: How UK brands write · SGR-011: Did brand writing change after ChatGPT?.