aboutsummaryrefslogtreecommitdiff
path: root/public/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html
diff options
context:
space:
mode:
Diffstat (limited to 'public/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html')
-rwxr-xr-xpublic/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html25
1 files changed, 11 insertions, 14 deletions
diff --git a/public/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html b/public/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html
index 107b062..0cb2ed4 100755
--- a/public/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html
+++ b/public/using-sentiment-analysis-for-clickbait-detection-in-rss-feeds.html
@@ -1,5 +1,5 @@
1<!doctype html><html lang=en-us><meta charset=utf-8><meta name=viewport content="width=device-width,initial-scale=1"><link href="data:image/x-icon;base64,AAABAAEAEBAAAAEAIABoBAAAFgAAACgAAAAQAAAAIAAAAAEAIAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAL69vf8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAv76+/8LBwQkAAAAAAAAAAAAAAAC+vb3/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAL+9vf/Bv78JAAAAAAAAAAAAAAAAu7q6/wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAC7ubr/vr29CAAAAAAAAAAAy8nJAZ6foP8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAnqGj/6GipAoAAAAAHLjU/xcXHf/BwsL/I8XY/yPK3v8XGiD/IbjL/yPF2f8XGiD/Fxkf/yLF2f8gnK3/Fxog/62ztv8fwNf/FRcd/x271v8mz93/GRsi/xkXHf8p097/GiIp/xobIv8p0t3/KdPe/xocIv8fYmr/KNPe/xoZH/8aHCL/J87c/xy81/8VFxz/IsPZ/8zS0/8XGiD/Ir/R/yPH2/8XGiD/Fxkf/yPH2/8dd4T/GBog/yPJ3f8jyNr/uru9/xcUGv8cudb/EhITDKi5vRKlvMP/RUpOERwcHRAdOj4QHTk8EBwdHRAdNTgQHTo/EBwcHRAcHB0QSGduEKW4vf+koqQfHzg+EBqz0ewSFRv7EyMr/xq51vsTERb7ExUb+xq41fsau9j7ExUb+xiPp/sZudb7ExUb+xMVG/sZuNX/GKvI/BIUGfMdvdn/IrfL/xcaIP8n1eb/J9Dh/xkcIf8ZGR7/J8/f/xxCSv8ZGyH/J9Dg/ybQ4P8ZHCL/FSQs/yPK3/8UExj/GE1b/ybS5P8ZGB7/Ghwj/ynW5P8p2Ob/Ghwi/yWrtv8p1eH/Ghwi/xocIv8p1uT/J8XT/xkcIv8m1un/Hb7d/xUYH/8hzOr/HtHu/xcaIf8XGB//I8vi/xgxOv8XGSD/I8rg/yPK4P8XGiD/GUFL/yPP6f8SERj/Fhkh/x3A4f8AAAAAJ2f9/ydr//8mZPH/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlYu38J2v//ydo/f8AAAAAAAAAAAd8/fkFqf//Iob8sAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAMY39awWr//8FfP3/AAAAAAAAAAAFm/7/SfD//wR+/f8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOB/f9B7v//BaX+/wAAAAAAAAAAQ878SAyZ/v9n1v4KAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADu9v8DDJb+/z3N/XgAAAAA3/sAAN/7AADf+wAA3/sAAAAAAAAAAAAAAAAAAN/7AAAAAAAAAAAAAAAAAAAAAAAAj/EAAI/5AACP8QAA3/sAAA==" rel=icon type=image/x-icon><title>Using sentiment analysis for clickbait detection in RSS feeds</title><meta name=description content="Initial thoughtsOne of the things that interested me for a while now is if major wellestablished news sites use click bait titles to drive additional traffic totheir sites and generate additional impressions."><link rel=alternate type=application/rss+xml title="Mitja Felicijan's posts" href=https://mitjafelicijan.com/index.xml><link rel=alternate type=application/rss+xml title="Mitja Felicijan's notes" href=https://mitjafelicijan.com/notes.xml><style>body{padding:1rem;max-width:760px;background:#fff;font-family:sans-serif;line-height:1.35rem;font-size:16px;margin:0 auto}hr{margin-block-start:1.5rem}h1,h2,h3{line-height:initial}h1{font-size:xx-large}footer{margin-block-start:2rem}cap{text-transform:capitalize}table{max-width:100%;width:100%;border-collapse:separate;border-spacing:2px;border:1px solid #000;border-left:1px solid #999;border-top:1px solid #999}blockquote{font-style:italic}table thead{background:#eee}ul.list li{padding:.2em 0}ul{line-height:1.4em}td,th{border:1px solid #000;padding:4px;border-right:1px solid #999;border-bottom:1px solid #999;text-align:left}pre{text-wrap:nowrap;overflow-x:auto;padding:0 1em;border:1px solid #dcdcdc}code{padding:0 3px;font-size:14px;border:0}pre code{line-height:1.3em}pre,code,pre *,code *{font-family:monospace}figure{margin-inline-start:0;margin-inline-end:0}figcaption{text-align:center}figcaption p{margin:.3em 0 0}img,video,audio{max-width:100%}header{display:flex;flex-direction:row;gap:3rem}nav{display:flex;gap:.75rem}nav.main{flex-grow:1}.pstatus-orange{background:gold}.pstatus-green{background:#9acd32}.pstatus-red{background:#cd5c5c}@media only screen and (max-width:600px){body{padding:15px}header{flex-direction:column;gap:1rem}a{word-wrap:break-word}}</style><header><nav class=main itemscope itemtype=http://schema.org/SiteNavigationElement role=toolbar><a href=/>Home</a> 1<!doctype html><html lang=en-us><meta charset=utf-8><meta name=viewport content="width=device-width,initial-scale=1"><link href="data:image/x-icon;base64,AAABAAEAEBAAAAEAIABoBAAAFgAAACgAAAAQAAAAIAAAAAEAIAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAL69vf8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAv76+/8LBwQkAAAAAAAAAAAAAAAC+vb3/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAL+9vf/Bv78JAAAAAAAAAAAAAAAAu7q6/wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAC7ubr/vr29CAAAAAAAAAAAy8nJAZ6foP8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAnqGj/6GipAoAAAAAHLjU/xcXHf/BwsL/I8XY/yPK3v8XGiD/IbjL/yPF2f8XGiD/Fxkf/yLF2f8gnK3/Fxog/62ztv8fwNf/FRcd/x271v8mz93/GRsi/xkXHf8p097/GiIp/xobIv8p0t3/KdPe/xocIv8fYmr/KNPe/xoZH/8aHCL/J87c/xy81/8VFxz/IsPZ/8zS0/8XGiD/Ir/R/yPH2/8XGiD/Fxkf/yPH2/8dd4T/GBog/yPJ3f8jyNr/uru9/xcUGv8cudb/EhITDKi5vRKlvMP/RUpOERwcHRAdOj4QHTk8EBwdHRAdNTgQHTo/EBwcHRAcHB0QSGduEKW4vf+koqQfHzg+EBqz0ewSFRv7EyMr/xq51vsTERb7ExUb+xq41fsau9j7ExUb+xiPp/sZudb7ExUb+xMVG/sZuNX/GKvI/BIUGfMdvdn/IrfL/xcaIP8n1eb/J9Dh/xkcIf8ZGR7/J8/f/xxCSv8ZGyH/J9Dg/ybQ4P8ZHCL/FSQs/yPK3/8UExj/GE1b/ybS5P8ZGB7/Ghwj/ynW5P8p2Ob/Ghwi/yWrtv8p1eH/Ghwi/xocIv8p1uT/J8XT/xkcIv8m1un/Hb7d/xUYH/8hzOr/HtHu/xcaIf8XGB//I8vi/xgxOv8XGSD/I8rg/yPK4P8XGiD/GUFL/yPP6f8SERj/Fhkh/x3A4f8AAAAAJ2f9/ydr//8mZPH/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlYu38J2v//ydo/f8AAAAAAAAAAAd8/fkFqf//Iob8sAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAMY39awWr//8FfP3/AAAAAAAAAAAFm/7/SfD//wR+/f8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOB/f9B7v//BaX+/wAAAAAAAAAAQ878SAyZ/v9n1v4KAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADu9v8DDJb+/z3N/XgAAAAA3/sAAN/7AADf+wAA3/sAAAAAAAAAAAAAAAAAAN/7AAAAAAAAAAAAAAAAAAAAAAAAj/EAAI/5AACP8QAA3/sAAA==" rel=icon type=image/x-icon><title>Using sentiment analysis for clickbait detection in RSS feeds</title><meta name=description content="Initial thoughtsOne of the things that interested me for a while now is if major wellestablished news sites use click bait titles to drive additional traffic totheir sites and generate additional impressions."><link rel=alternate type=application/rss+xml title="Mitja Felicijan's posts" href=https://mitjafelicijan.com/index.xml><link rel=alternate type=application/rss+xml title="Mitja Felicijan's notes" href=https://mitjafelicijan.com/notes.xml><style>body{padding:1rem;max-width:760px;background:#fff;font-family:sans-serif;line-height:1.35rem;font-size:16px;margin:0 auto}hr{margin-block-start:1.5rem}h1,h2,h3{line-height:initial}h1{font-size:xx-large}footer{margin-block-start:2rem}cap{text-transform:capitalize}table{max-width:100%;width:100%;border-collapse:separate;border-spacing:2px;border:1px solid #000;border-left:1px solid #999;border-top:1px solid #999}blockquote{font-style:italic}table thead{background:#eee}ul.list li{padding:.2em 0}ul{line-height:1.4em}td,th{border:1px solid #000;padding:4px;border-right:1px solid #999;border-bottom:1px solid #999;text-align:left}pre{text-wrap:nowrap;overflow-x:auto;padding:0 1em;border:1px solid #dcdcdc}code{padding:0 3px;font-size:14px;border:0}pre code{line-height:1.3em}pre,code,pre *,code *{font-family:monospace}figure{margin-inline-start:0;margin-inline-end:0}figcaption{text-align:center}figcaption p{margin:.3em 0 0}img,video,audio{max-width:100%}header{display:flex;flex-direction:row;gap:3rem}nav{display:flex;gap:.75rem}nav.main{flex-grow:1}.pstatus-orange{background:gold}.pstatus-green{background:#9acd32}.pstatus-red{background:#cd5c5c}@media only screen and (max-width:600px){body{padding:15px}header{flex-direction:column;gap:1rem}a{word-wrap:break-word}}</style><header><nav class=main itemscope itemtype=http://schema.org/SiteNavigationElement role=toolbar><a href=/>Home</a>
2<a href=https://files.mitjafelicijan.com/ target=_blank>Files</a> 2<a href=/vault.html>Vault</a>
3<a href=/mitjafelicijan.pgp.pub.txt target=_blank>PGP</a> 3<a href=/mitjafelicijan.pgp.pub.txt target=_blank>PGP</a>
4<a href=/curriculum-vitae.html>CV</a> 4<a href=/curriculum-vitae.html>CV</a>
5<a href=/index.xml target=_blank>RSS</a></nav></header><main role=main><article itemtype=http://schema.org/Article><h1 itemtype=headline>Using sentiment analysis for clickbait detection in RSS feeds</h1><p><cap>post</cap>, Oct 19, 2019 on <a href=https://mitjafelicijan.com>Mitja Felicijan's blog</a><div><h2 id=initial-thoughts>Initial thoughts</h2><p>One of the things that interested me for a while now is if major well 5<a href=/index.xml target=_blank>RSS</a></nav></header><main role=main><article itemtype=http://schema.org/Article><h1 itemtype=headline>Using sentiment analysis for clickbait detection in RSS feeds</h1><p><cap>post</cap>, Oct 19, 2019 on <a href=https://mitjafelicijan.com>Mitja Felicijan's blog</a><div><h2 id=initial-thoughts>Initial thoughts</h2><p>One of the things that interested me for a while now is if major well
@@ -46,21 +46,18 @@ article.<pre tabindex=0 style=background-color:#fff><code><span style=display:fl
46learning we would be able to get better insights.<li><strong>Next step would be to</strong> periodically fetch RSS items and store them over a 46learning we would be able to get better insights.<li><strong>Next step would be to</strong> periodically fetch RSS items and store them over a
47longer period of time and then perform analysis again and use either machine 47longer period of time and then perform analysis again and use either machine
48learning or deep learning on top of it.</ol><figure><img src=/posts/sentiment-analysis/guardian-sa-title-desc-relationship.png alt="Relationship between title and description"></figure><p>Figure above displays difference between title and description sentiment for 48learning or deep learning on top of it.</ol><figure><img src=/posts/sentiment-analysis/guardian-sa-title-desc-relationship.png alt="Relationship between title and description"></figure><p>Figure above displays difference between title and description sentiment for
49specific RSS feed item. 1 means positive and -1 means negative sentiment.<p><a href=/posts/sentiment-analysis/sentiment-analysis.ipynb>» Download Jupyter Notebook</a><h2 id=going-further>Going further</h2><ul><li><a href=https://github.com/bswiss/news_mood>Twitter Sentiment Analysis by Bryan Schwierzke</a><li><a href=https://github.com/thisandagain/sentiment>AFINN-based sentiment analysis for Node.js by Andrew Sliwinski</a><li><a href=https://github.com/adeshpande3/LSTM-Sentiment-Analysis>Sentiment Analysis with LSTMs in Tensorflow by Adit Deshpande</a><li><a href=https://github.com/abdulfatir/twitter-sentiment-analysis>Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc. by Abdul Fatir</a></ul></div></article></main><section><hr><h2>Posts from blogs I follow around the net</h2><ul><li><a href=https://chotrin.org/writing/2023-10-20.html target=_blank rel=noopener>OpenBSD upgrade and fall things.</a><div>Been AFK for a bit. It's autumn and I upgraded this server to OpenBSD 7.4! — <a href=https://chotrin.org>chötrin's wiki.</a><li><a href=https://mirzapandzo.com/next-image-url-parameter-is-valid-but-upstream-response-is-invalid target=_blank rel=noopener>Next/Image "url" parameter is valid but upstream response is invalid</a><div>Getting "url" parameter is valid but upstream response is invalid error with Next/Image on WSL2 — <a href=https://mirzapandzo.com/>Mirza Pandzo's Blog</a><li><a href=https://drewdevault.com/2023/10/13/Going-off-script.html target=_blank rel=noopener>Going off-script</a><div>There is a phenomenon in society which I find quite bizarre. Upon our entry to 49specific RSS feed item. 1 means positive and -1 means negative sentiment.<p><a href=/posts/sentiment-analysis/sentiment-analysis.ipynb>» Download Jupyter Notebook</a><h2 id=going-further>Going further</h2><ul><li><a href=https://github.com/bswiss/news_mood>Twitter Sentiment Analysis by Bryan Schwierzke</a><li><a href=https://github.com/thisandagain/sentiment>AFINN-based sentiment analysis for Node.js by Andrew Sliwinski</a><li><a href=https://github.com/adeshpande3/LSTM-Sentiment-Analysis>Sentiment Analysis with LSTMs in Tensorflow by Adit Deshpande</a><li><a href=https://github.com/abdulfatir/twitter-sentiment-analysis>Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc. by Abdul Fatir</a></ul></div></article></main><section><hr><h2>Posts from blogs I follow around the net</h2><ul><li><a href=https://chotrin.org/writing/2023-10-29.html target=_blank rel=noopener>even more bike things.</a><div>I wrote about all sorts of biking and not-biking things in my life this week. — <a href=https://chotrin.org>chötrin's wiki.</a><li><a href="http://offbeatpursuit.com:80/blog/?id=25" target=_blank rel=noopener>A fix by any other name</a><div>tags:
50i2c, plan9
51Another month, another file system.
52Well, if you can’t fix it in software, fix it in hardware (looking at
53you, bme680, we’re not
54done yet). The show mu… — <a href=http://offbeatpursuit.com:80/blog/>WLOG - blog</a><li><a href=https://mirzapandzo.com/next-image-url-parameter-is-valid-but-upstream-response-is-invalid target=_blank rel=noopener>Next/Image "url" parameter is valid but upstream response is invalid</a><div>Getting "url" parameter is valid but upstream response is invalid error with Next/Image on WSL2 — <a href=https://mirzapandzo.com/>Mirza Pandzo's Blog</a><li><a href=https://drewdevault.com/2023/10/13/Going-off-script.html target=_blank rel=noopener>Going off-script</a><div>There is a phenomenon in society which I find quite bizarre. Upon our entry to
50this mortal coil, we are endowed with self-awareness, agency, and free will. 55this mortal coil, we are endowed with self-awareness, agency, and free will.
51Each of th… — <a href=https://drewdevault.com>Drew DeVault's blog</a><li><a href=https://solar.lowtechmagazine.com/2023/10/workshop-in-rotterdam-how-to-build-a-bike-generator/ target=_blank rel=noopener>Workshop in Rotterdam: How to Build a Bike Generator</a><div>Afbeelding: Low-tech Magazine workshop in Rotterdam, the Netherlands. Poster: Marie Verdeil. Image: Sara Vercauteren 56Each of th… — <a href=https://drewdevault.com>Drew DeVault's blog</a><li><a href=https://solar.lowtechmagazine.com/2023/10/thematic-book-series-how-to-downsize-a-transport-network/ target=_blank rel=noopener>Thematic Book Series: How to Downsize a Transport Network?</a><div>Image: Book cover. [How to downsize a transport network?](https://www.lulu.com/shop/kris-de-decker/how-to-downsize-a-transport-network/paperback/product-42n4p7.htm… — <a href=https://solar.lowtechmagazine.com/posts/>LOW←TECH MAGAZINE English</a><li><a href=https://neil.computer/notes/chart-of-accounts-for-startups-and-saas-companies/ target=_blank rel=noopener>Chart of Accounts for Startups and SaaS Companies</a><div>Accounting is fundamental to starting a business. You need to have a basic understanding of accounting principles and essential bookkeeping. I had to learn it. Ther… — <a href=https://neil.computer/>Neil Panchal</a><li><a href=https://journal.valeriansaliou.name/deploy-a-nomad-cluster-on-alpine-linux-with-vultr/ target=_blank rel=noopener>Deploy a Nomad Cluster on Alpine Linux with Vultr</a><div>After spending countless hours trying to understand how to deploy my apps on Kubernetes for the first time to host Mirage, an AI API service that I run, I ended up … — <a href=https://journal.valeriansaliou.name/>Valerian Saliou</a><li><a href=https://jcs.org/2023/10/25/wifi_da target=_blank rel=noopener>BlueSCSI Wi-Fi Desk Accessory 1.0 Released</a><div>BlueSCSI Wi-Fi Desk Accessory
52The workshop takes place on behalf of the “Hou… — <a href=https://solar.lowtechmagazine.com/posts/>LOW←TECH MAGAZINE English</a><li><a href="http://offbeatpursuit.com:80/blog/?id=24" target=_blank rel=noopener>Printf debugging</a><div>tags:
53plan9
54There’s no shame in that. Yes, there is documentation, code to be
55read, and debuggers to be used. But sometimes you just need to “see”
56what is happening.
57So… — <a href=http://offbeatpursuit.com:80/blog/>WLOG - blog</a><li><a href=https://neil.computer/notes/chart-of-accounts-for-startups-and-saas-companies/ target=_blank rel=noopener>Chart of Accounts for Startups and SaaS Companies</a><div>Accounting is fundamental to starting a business. You need to have a basic understanding of accounting principles and essential bookkeeping. I had to learn it. Ther… — <a href=https://neil.computer/>Neil Panchal</a><li><a href=https://journal.valeriansaliou.name/deploy-a-nomad-cluster-on-alpine-linux-with-vultr/ target=_blank rel=noopener>Deploy a Nomad Cluster on Alpine Linux with Vultr</a><div>After spending countless hours trying to understand how to deploy my apps on Kubernetes for the first time to host Mirage, an AI API service that I run, I ended up … — <a href=https://journal.valeriansaliou.name/>Valerian Saliou</a><li><a href=https://jcs.org/2023/10/17/wikipedia target=_blank rel=noopener>Wikipedia Reader 1.0 Released</a><div>Wikipedia Reader
581.0 has been released: 571.0 has been released:
59wikipedia-1.0.sit 58wifi_da-1.0.sit
60(StuffIt 3 archive, includes 59(StuffIt 3 archive)
61source code 60SHA256: ccfc9d27dd5da7412d10cef73b81119a1fec3848e4d1d88ff652a07ffdc6a69aSHA1:… — <a href=https://jcs.org/>joshua stein</a></ul><p><a href=https://git.sr.ht/~sircmpwn/openring>Generated with openring.</a></section><footer><hr><p><big><strong>Want to comment or have something to add?</strong></big><p>You can write me an email
62and THINK C 5 project file)
63SHA256: 360e12d064f6579695f1e627ce34cb2f0… — <a href=https://jcs.org/>joshua stein</a></ul><p><a href=https://git.sr.ht/~sircmpwn/openring>Generated with openring.</a></section><footer><hr><p><big><strong>Want to comment or have something to add?</strong></big><p>You can write me an email
64at <a href=mailto:mitja.felicijan@gmail.com>mitja.felicijan@gmail.com</a> or 61at <a href=mailto:mitja.felicijan@gmail.com>mitja.felicijan@gmail.com</a> or
65catch up with me <a href=https://telegram.me/mitjafelicijan target=_blank>on Telegram</a>.<hr><p>This website does not track you. Content is made available under 62catch up with me <a href=https://telegram.me/mitjafelicijan target=_blank>on Telegram</a>.<hr><p>This website does not track you. Content is made available under
66the <a href=https://creativecommons.org/licenses/by/4.0/ target=_blank rel=noreferrer>CC BY 4.0 license</a> unless specified 63the <a href=https://creativecommons.org/licenses/by/4.0/ target=_blank rel=noreferrer>CC BY 4.0 license</a> unless specified