47news.jp 37 F
🛡️ SEO 42 🤖 GEO 65 ⚡ Perf 33 🏗️ Arch 67

47news.jp — Global SEODiff Score 37/100

47news.jp
📊

47news.jp registers just 15/100 on the ACRI scale — a bottom-tier result indicating systemic AI visibility problems. In the infrastructure sector, 47news.jp underperforms relative to the average (57), indicating room for competitive improvement. The low ghost ratio (5%) confirms that what crawlers see matches what users see — a hallmark of strong SSR implementation. A 23.6× token bloat ratio means crawlers must process significantly more tokens to reach the actual content — a drag on extraction efficiency. No structured data was detected, which means AI systems must infer all entities and relationships from raw HTML alone. A full AI bot restriction means AI-powered search and answer engines cannot currently crawl and index this domain's content.

37
F — Global SEODiff Score
Comprehensive search visibility assessment
Significant improvement opportunities. Start with Performance (33).
🎯 Top Fix: Allow GPTBot + ClaudeBot in robots.txt → lift the score cap
🔬 Automated SEODiff Assessment · Snapshot: Feb 28, 2026 · 📋 API
📈 ACRI Trend 25 snapshots
Feb 22 Feb 28
🔔 Recent AI Indexing Activity
No recent changes detected by adaptive crawler.
Does your site score higher than 47news.jp?
Run the same 40-signal audit on your own domain — free, instant results.
Scan Your Site Free →
🧮 Score Transparency — How is this calculated?
🛡️ Traditional SEO (25% weight)42 × 0.25 = 10.5
🤖 AI Readiness / GEO (40% weight)65 × 0.40 = 26.0
⚡ Performance (20% weight)33 × 0.20 = 6.6
🏗️ Architecture & Trust (15% weight)67 × 0.15 = 10.0
Weighted sum = 10.5 + 26.0 + 6.6 + 10.0
⚠️ Fatal multiplier: All major AI bots blocked → ×0.5
Global SEODiff Score = 37 (F)
🚫
Gatekeeper Rule: Score cannot exceed 15. Both GPTBot and ClaudeBot are blocked in robots.txt. No major AI assistant can cite this site. Allow at least one major AI crawler to lift the cap. See Bot Access →
📊 ACRI Sub-Scores (AI Readiness Detail)
20
Bot Access
avg 92
99
Rendering
avg 93
100
Structure
avg 36
0
Schema
avg 9
70
Tech Stack
avg 63
🔀
Visibility Delta: Google vs AI
Google (Tranco)
Top 1.0%
Rank #9819
+67 pts
Gap
AI (ACRI)
Top 67%
Score 15/100

47news.jp punches above its weight in AI — AI visibility exceeds Google ranking. This is a competitive moat worth protecting. ACRI measures technical crawler readiness. Read the methodology →

Why 47news.jp ranks here

Tech stackNext.js
RenderingSSR
Schema coverage0 blocks
Token bloat23.6×

Fastest improvements

  • Allow GPTBot in robots.txt so AI crawlers can access your pages (see Crawl Access).
  • Allow ClaudeBot (many assistants rely on it) — blocking it often correlates with “AI invisibility.”
  • Add basic Organization and WebSite JSON-LD to fix “0 schema blocks” (see Schema Coverage).
  • Reduce token bloat (navigation/footer/code) so agents reach your main content faster (see Token Bloat).
  • Create an llms.txt file so AI crawlers can discover your content structure without heavy crawling. Generate llms.txt →
  • Run a full entropy audit to find which DOM regions waste the most tokens. Run Entropy Audit →
🧪

JavaScript Rendering Check

We check what AI crawlers miss when they skip JavaScript execution.

Running headless browser to simulate AI extraction…
🛡️

Traditional SEO

42/100 25 % of Global Score 🟢 High Confidence

📝 Title Tag

65 chars
Too long

Optimal range: 30–60 characters for SERP display.

📋 Meta Description

341 chars
Too long

Optimal range: 120–160 characters for snippet control.

🔤 Heading Hierarchy

  • ✓ Exactly 1 <h1> tag — found 1
  • ✓ Has <h2> headings — found 22
  • ✓ <h2> not before <h1>

🔍 Indexability

  • ✓ Canonical tag present → https://www.47news.jp/
  • ✓ No noindex directive
  • ✓ Meta viewport set
  • ✓ HTML lang attribute → ja
  • ✗ Hreflang tags
  • ✓ Googlebot allowed by robots.txt

🌐 Social / OpenGraph

  • ✓ og:title — 47NEWS(よんななニュース)
  • ✓ og:description — 全国47都道府県・52参加新聞社と共同通信の内外ニュース。地方創生・写真・動画。地域の文化や活力を発信。野球、サッカー、ゴルフなどスポーツも地域密着から五輪まで。新商品・技術、観光、B級グルメ、映画、音楽、新刊、心和む記事コーナーなど
  • ✓ og:image — preview
  • ✗ twitter:card
📐 How the SEO Pillar score is calculated

SEO Pillar = Title (20 pts) + Meta Desc (20 pts) + Heading Hierarchy (20 pts) + Indexability (20 pts) + Social/OG (20 pts)

Each sub-score is derived from the checks above. Canonical tag, lang attribute, og:image, and a single H1 are the highest-impact items.

🤖

AI Readiness / GEO

65/100 40 % of Global Score 🟡 Medium Confidence

This pillar aggregates citation share, hallucination risk, bot access, schema health, and content extractability. The individual diagnostic sections below contribute to this score.

🔗

Citation Alternatives

Research
💡
Insight: In the infrastructure sector, safely.co.jp (ACRI: 90) currently has stronger AI extractability. AI models tend to prefer sources with higher semantic structure and schema coverage. Domains with ACRI < 40 see 3.5× more hallucinations. Read the research →
47news.jp
56
Your ACRI Score
90
Industry Peer ACRI
AI models prioritize pages with strong semantic structure and schema coverage. safely.co.jp has schema coverage of 3 blocks and uses WordPress. Improve your score by implementing the remediation patches below.
📊 Side-by-Side Comparison →
🚨

Hallucination Risk

Research

Is AI lying about your brand? This panel measures how likely LLMs are to hallucinate facts when extracting information from your page.

Analyzing hallucination risk…

🤖 Bot Access Matrix

GPTBot (OpenAI)
Blocked
ClaudeBot (Anthropic)
Blocked
CCBot (Common Crawl)
Blocked
Google-Extended
Blocked
Googlebot
Allowed
💡GPTBot is blocked. To appear in ChatGPT citations, add Allow: / under User-agent: GPTBot in your robots.txt.
💡ClaudeBot is blocked. To be cited by Claude, allow ClaudeBot in robots.txt.

👻 Rendering (Ghost Ratio) Docs

Ghost Ratio 5%
0% — Safe 50% 100% — Risk
Status Server-Side Rendered (Safe)
Rendering Type SSR

📊 Structure & Information Density Docs

Structure Grade 100/100 — Excellent
Structured Elements 308 elements (308 lists, 0 rows, 0 headers)
Total Words819
Raw Density37.6%

🏷️ Schema Health Docs

Organization Schema ❌ Missing
Product / Service Schema ⚠️ Not Found
Total Schema Blocks0 — No JSON-LD detected

Schema Coverage Map

0/7 schema types detected
❌ Organization
❌ Product/Service
❌ Breadcrumb
❌ FAQ
❌ Article
❌ WebSite
💡Organization schema missing. AI models cannot identify your brand entity. Without it, your brand won't appear in Knowledge Panels or be associated with your content.
💡Product / Service schema missing. AI models don't know this is a SaaS product. Add Product or SoftwareApplication schema so AI understands what you offer and can surface pricing/features.
💡BreadcrumbList schema missing. AI cannot understand your site hierarchy or how pages relate to each other.
💡FAQ schema missing. Adding FAQPage schema lets AI models directly extract Q&A pairs for Featured Snippets and chatbot answers.
💡WebSite schema missing. Add WebSite + SearchAction so Google can generate a Sitelinks Search Box for your brand in AI results.

📐 AI Efficiency Metrics Docs

59
AI Extractability
High
Crawl Cost
Critical
Blocklist Risk
Extractability59/100 — AI models can partially extract answers from this page
Crawl CostHigh (75/100) — expensive for AI crawlers to process
Blocklist RiskCritical — 4 of 5 AI crawlers blocked

Token Bloat Research

4%
🗑️ 96%
Useful Content (20.3 KB)Bloat (456.9 KB)
Token Bloat Ratio23.6× — Heavy

Multimodal Readiness

Visual Context84% Optimized for Vision
Image Alt Coverage210 / 249 images have alt text

TDM Rights

TDM-Reservation HeaderNot set
X-Robots-Tag: noaiNot set
💡Your HTML is 477.2 KB, but only 20.3 KB is text. 4% useful / 96% bloat. AI crawlers have limited context windows (e.g. 128k tokens). This level of bloat (23.6×) risks context-window truncation by ChatGPT, Claude, and Gemini. Reduce inline scripts, CSS, hydration payloads, and tracking code.

🔥 Structural Entropy Check Research

0 Entropy
Poor Token Bloat: High
Noise Ratio: 95.8% · SNR: 0.04 · Signal: 5184 / Noise: 116971 tokens

🔬 AI-Crawler Simulation

See your website the way AI crawlers do. CSS stripped, structure labeled, content chunked.

🌐
This is what humans see — styled, branded, visual.
Toggle to "AI Agent View" to see what GPTBot, ClaudeBot, and other AI crawlers actually extract from this page.
🤖

AI Answer Preview

NEW

See how AI models summarize your site. Left: your actual content. Right: what the LLM extracts and says about you.

Simulating AI extraction…
🧠

The LLM Interpretation

AI-VERIFIED

A local LLM (mlx-community/gemma-3-4b-it-qat-4bit) analyzed the extracted content of 47news.jp and produced this structured business intelligence. Fields marked SEMANTIC VOID indicate information the AI could not find — a critical gap in your site’s machine-readability.

Core Offering
This text focuses on news and articles related to the city of Niihama in Ehime Prefecture, Japan, including local events,
Target Audience
Local residents of Niihama and Ehime Prefecture, tourists interested in the region's culture and food, and readers of the China Shimbun newspaper.
Pricing Model
⚠ SEMANTIC VOID
🏆 Competitive Moat
SEMANTIC VOID
📊 Content Depth
3/10
⚡ Key Pain Points
• Lack of a clear product description or offering.
• Limited information about any potential business model.
Model: mlx-community/gemma-3-4b-it-qat-4bit · Analyzed: 2026-02-28 · Data extracted from the site’s main content via strict JSON prompting.

🔧 Tech Stack

FrameworkNext.js
AI-Readiness Score70/100
ServerAmazonS3
CDN
HTTP Status200
Load Time1685 ms
Raw HTML Size477.2 KB
Visible Text Size20.3 KB

Performance & Speed

33/100 20 % of Global Score 🟢 High Confidence

⏱️ Time to First Byte

1685 ms
Slow — bots may time out or deprioritise

Google considers <200 ms "good". AI crawlers may have even shorter timeouts.

📦 Page Weight

3440
DOM nodes
477 KB
HTML payload
Heavy page — consider reducing DOM complexity

🗄️ Cache & CDN

  • ✓ Cache-Control header → public, max-age=0, s-maxage=11, must-revalidate
  • ✗ CDN cache status
  • ✗ CDN detected

🔬 Tracker Tax

1
tracker scripts
1
third-party domains
0.0%
token overhead
Minimal tracker load — clean signal for bots
doubleclick.net
📐 How the Performance Pillar score is calculated

Perf Pillar = TTFB (35 pts) + Page Weight (25 pts) + Cache/CDN (20 pts) + Tracker Tax (20 pts)

TTFB <200 ms = full marks. DOM >3000 or payload >300 KB incurs heavy penalties. Tracker scripts beyond 5 reduce score.

🏗️

Architecture & Trust

67/100 15 % of Global Score 🟡 Medium Confidence

🗺️ Sitemap & Robots

  • ✗ Sitemap declared in robots.txt
  • ✓ Googlebot allowed
  • ✗ GPTBot allowed
  • ✗ ClaudeBot allowed

🔗 Linking

371
internal links
88
external links
Good internal linking — helps crawlers discover content

🔒 Security & Trust

  • ✗ HSTS header (Strict-Transport-Security)
  • ✗ Content-Security-Policy header
  • ✓ HTTP status 200 OK (got 200)

♿ Accessibility Signals

  • ✓ HTML lang attribute → ja
  • ✓ Meta viewport for mobile
  • ✓ Single H1 for screen readers
📐 How the Architecture Pillar score is calculated

Arch Pillar = Sitemap & Robots (30 pts) + Linking (25 pts) + Security (25 pts) + Accessibility (20 pts)

Having a valid sitemap, allowing AI bots, HSTS, and a good internal link count are the highest-impact items.

🏅 AI-Verified Trust Badge

Your site scores 56/100. Reach 80+ to unlock the green "AI-Verified" badge. Fix the issues below to improve your score.

AI-Verified badge for 47news.jp
Pending Audit — score below 80 threshold
<a href="https://seodiff.io/radar/domains/47news.jp" rel="noopener"><img src="https://seodiff.io/api/v1/badge?domain=47news.jp" alt="AI-Verified by SEODiff" width="280" height="52"></a>

💡 Paste in your site footer, GitHub README, or email signature. Badge updates automatically as your score changes.

� Deep Crawl Analysis 162 pages · Deep-10

Homepage ACRI
56
Single-page score
-17
Moderate hidden bloat
Δ delta
Site-Wide ACRI
39
Avg across 162 pages · Range 37–48
🔍
Hidden Bloat Detected

Homepage scores 56, but internal pages average only 39 — a -17-point gap. Blogs, docs, and legacy content are dragging down AI readability site-wide.

Topical Cohesion
7%
Topical Drift
TF-IDF cosine similarity
Total Words
28746
Avg Bloat
291.6×
Page Type ACRI Token Bloat Words Status
https://www.47news.jp/13935651.html
ヴォルターズ大勝 奈良に101-63 今季最多得点差 バスケB2|47NEWS(よんななニュース)
other 48 261.1× 204
https://www.47news.jp/13935798.html
堀島、W杯で観客沸かせる勝利 「日本にとっていい日」|47NEWS(よんななニュース)
other 48 252.0× 212
https://www.47news.jp/13936085.html
〈ツエーゲン金沢 百年構想リーグ〉ホーム開幕、4894人沸く ゴースタ 今季初の90分勝利|47NEWS(よんななニュース)
other 48 298.7× 214
https://www.47news.jp/13935545.html
WBC代表2チームに県産品贈呈 2日から宮崎市で強化試合|47NEWS(よんななニュース)
other 48 263.6× 203
https://www.47news.jp/13935683.html
宇都宮ブレックスは3位に 3人制バスケ国際リーグ「スーパープレミア」序盤リードも…実力十分、課題はメンタル|47NEWS(よんななニュース)
other 48 260.1× 209
https://www.47news.jp/13922214.html
宮島口にカキ小屋が3月オープン カキ大量死でも「おいしさは健在と伝えたい」|47NEWS(よんななニュース)
other 48 272.0× 201
https://www.47news.jp/13930807.html
バナナを買ってツエーゲン応援 薄井青果とコラボ 「ゲンゾー」絵柄をパッケージに|47NEWS(よんななニュース)
other 48 260.4× 208
https://www.47news.jp/13929737.html
冨高日向子2位、堀島行真は3位 富山でW杯モーグル第6戦|47NEWS(よんななニュース)
other 48 278.7× 202
https://www.47news.jp/13930641.html
鹿島、3連勝で東首位 J1百年構想リーグ|47NEWS(よんななニュース)
other 48 264.2× 216
https://www.47news.jp/13930748.html
大谷、連日のフリー打撃 9本柵越え、5階席への当たりも|47NEWS(よんななニュース)
other 48 273.8× 206
https://www.47news.jp/13930489.html
首位NEC川崎が29勝目 バレーSVリーグ|47NEWS(よんななニュース)
other 48 271.3× 204
https://www.47news.jp/13930136.html
【速報】柏レイソル初勝利 垣田、瀬川がゴール 2—0でFC東京下す J1百年構想リーグ|47NEWS(よんななニュース)
other 48 246.5× 223
https://www.47news.jp/13934460.html
Wソックス村上が日本代表合流 2日から大リーガー出場|47NEWS(よんななニュース)
other 48 283.2× 202
https://www.47news.jp/13934416.html
【速報】村上がWBC日本代表に合流|47NEWS(よんななニュース)
other 48 259.8× 206
https://www.47news.jp/13933156.html
大谷グラブで白熱プレー 児童ら野球大会/藤崎|47NEWS(よんななニュース)
other 48 259.3× 205
https://www.47news.jp/13932420.html
女子サッカー日本一の柳ケ浦高「一戦必勝で戦えた」 大分市で祝勝会、部員ら出席【大分県】|47NEWS(よんななニュース)
other 48 283.5× 203
https://www.47news.jp/13932153.html
ジャンプ二階堂、ドバイで足止め 米などのイラン攻撃影響で|47NEWS(よんななニュース)
other 48 270.4× 207
https://www.47news.jp/13934647.html
【速報】WBC、写真や動画の投稿禁止|47NEWS(よんななニュース)
other 38 291.8× 176
https://www.47news.jp/13934724.html
中9―2D(1日) 中日が11安打、細川3打点|47NEWS(よんななニュース)
other 38 331.0× 136
https://www.47news.jp/13934852.html
二階堂蓮はドバイで足止め サッカー、バスケ試合延期|47NEWS(よんななニュース)
other 38 292.5× 194
Showing 20 of 100 pages. Unlock full subpage table →
📂
Health by Sub-Directory
Average ACRI and top issues aggregated by URL path prefix
Path Pages Avg ACRI Ghost % Bloat Top Issue
/13935651.html/ 1 48 1% 261.1× Bot Blocked
/13932512.html/ 1 38 1% 271.5× Bot Blocked
/13931363.html/ 1 38 1% 277.0× Bot Blocked
/13930592.html/ 1 38 1% 280.5× Bot Blocked
/13930011.html/ 1 38 1% 286.3× Bot Blocked
/13932140.html/ 1 38 1% 314.7× Bot Blocked
/13933127.html/ 1 38 1% 289.4× Bot Blocked
/13930807.html/ 1 48 1% 260.4× Bot Blocked
/13935084.html/ 1 38 1% 279.1× Bot Blocked
/13935097.html/ 1 38 1% 308.9× Bot Blocked
/13927473.html/ 1 38 1% 324.4× Bot Blocked
/13928463.html/ 1 38 1% 274.3× Bot Blocked
/13934315.html/ 1 38 1% 275.2× Bot Blocked
/13928321.html/ 1 37 1% 374.8× Bot Blocked
/13930136.html/ 1 48 1% 246.5× Bot Blocked
🔗
Outbound External Citations
0 unique external domains cited across 162 pages
sankei.com ×162
t.pia.jp ×162
chiikisaisei.jp ×162
sakigake.jp ×162
minpo.jp ×162
smile-tohoku.jp ×162
mall.373news.com ×162
tchina.kyodonews.net ×162
🔄 Re-Crawl & Update 📡 Track this Domain

Scores update automatically each month. Create a free account for on-demand re-crawls (3/month free).

🔌 API Access

Pull this data programmatically. All sub-page metrics are available via our public API.

curl https://seodiff.io/api/v1/deep10/domain/47news.jp

Get your free API key — 100 requests/month included.

🔗 Similar infrastructure Sites

Domains with a similar tech stack, industry, and AI readiness profile to 47news.jp. Compare side-by-side.

Domain ACRI AI Score Tech Stack Token Bloat Schema
47news.jp (this site) 56 15 Next.js 23.6× 0
hl-grosshandel.com 81 82 Laravel 1.9× 1 Compare →
roperrhodes.co.uk 81 85 Custom / Proprietary 1.9× 1 Compare →
arzancell.com 81 90 WordPress 8.1× 2 Compare →
teteamodeler.com 81 85 Express 1.9× 2 Compare →
msg.de 81 85 Custom / Proprietary 2.6× 2 Compare →
Compare All 5 Similar Sites →

📊 Semantic Share of Voice

How often would an AI cite 47news.jp when users ask about topics in this domain's niche? We run entity queries through our 188k-page search index and measure citation probability.

Analyzing citation landscape…

🩹

Remediation Patches

COPY-PASTE

Auto-generated code fixes tailored to 47news.jp. Copy and paste these into your codebase to improve AI visibility. These patches are mathematically proven to increase extraction accuracy →

Add Organization JSON-LD
High Impact ⏱ 5 min
AI models cannot identify your brand entity without Organization schema. This is the #1 fix for AI visibility.
html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "47news",
  "url": "https://47news.jp",
  "logo": "https://47news.jp/lib/common/img/favicon.ico",
  "sameAs": []
}
</script>
Add WebSite + SearchAction JSON-LD
High Impact ⏱ 5 min
Enables the Sitelinks Search Box in Google and allows AI to understand your site structure.
html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "WebSite",
  "name": "47news",
  "url": "https://47news.jp",
  "potentialAction": {
    "@type": "SearchAction",
    "target": "https://47news.jp/search?q={search_term_string}",
    "query-input": "required name=search_term_string"
  }
}
</script>
Allow GPTBot in robots.txt
High Impact ⏱ 2 min
GPTBot is blocked — your content cannot appear in ChatGPT citations. Add this to your robots.txt:
text
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /
Allow ClaudeBot in robots.txt
Medium Impact ⏱ 2 min
ClaudeBot is restricted — Claude may not be able to cite your content. Many AI assistants rely on it.
text
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /
Reduce Token Bloat
Medium Impact ⏱ 1–2 hrs
Only 4% of your HTML is useful content. AI crawlers waste context window tokens on bloat.
html
<!-- Move inline CSS to external stylesheets -->
<link rel="stylesheet" href="/css/main.css">

<!-- Move inline scripts to external files with defer -->
<script src="/js/app.js" defer></script>

<!-- Remove duplicate navigation blocks -->
<!-- Keep only ONE <nav> in the <header> -->

<!-- Ensure <main> wraps your primary content -->
<main>
  <!-- Your content here — this is what AI sees first -->
</main>
📈

Projected Impact

ROI EST.

If you apply the patches above, here's the estimated improvement for 47news.jp:

Current Score
15
Projected Score
46
Improvement
+31 pts
Allow GPTBot +8 pts
Allow ClaudeBot +5 pts
Add Organization schema +6 pts
Add WebSite schema +4 pts
Reduce token bloat +5 pts
Add FAQ schema +3 pts

*Estimates based on SEODiff's scoring model. Actual results depend on implementation quality.

📋 Data Export

Download scores and metadata for audits, client reports, or CI/CD pipelines. Exports contain computed metrics only (no copyrighted content).

All data is generated automatically and updated with each crawl. JSON exports contain scores and metadata only (no copyrighted content).

Is this your company?

Monitor your AI visibility score weekly and get alerted when changes happen.

Start Free →

🧭 Self-Diffing (Private Layer)

For owned domains, combine this world snapshot with private drift + regression history.
Template Drift
Track in My Site
Drift → Traffic Impact
In development coming soon
Regression Incidents
Track in My Site
Internal Linking
Deep Audit graph
Semantic Structure
GEO view in Deep Audit
Content Quality
Thin/duplicate tracking

🕒 History

Score over timeAvailable in My Site history
Drift eventsTemplate timeline + incidents
Drift → Revenue AttributionComing soon
Schema/rendering/extractability changesTracked per scan in project history