{"topic":{"id":7278,"title":"Ideas behind requiring login to browse","slug":"topic","userId":1047,"categoryId":2,"createdAt":"2023-11-16 01:22:08.417041","bumpedAt":"2023-11-16 14:46:09.990071","views":408,"postsCount":8,"highestPostNumber":8,"likeCount":0,"closed":false,"pinned":false,"pinnedGlobally":false,"pinnedAt":null,"pinnedUntil":null,"isBanner":false,"excerpt":"The main purpose is to eventually provide a tailored experience for our users, by learning a recommendation system from historical browsing data. Currently, we only recommend related topics on the bottom of the page by d…","deletedAt":null,"isAnonymous":false,"isPrivate":false,"isMembersOnly":false,"category":{"id":2,"name":"网站","slug":"website","color":"986a44"},"author":{"id":1047,"username":"anonymous_coward_old","name":"Anonymous Coward Old","avatarUrl":"/uploads/image/43/32/4332638c11248b8ff07033c11de0759a55205facfbec85e14458245a91991faf.avif"},"realAuthor":{"id":1047,"username":"anonymous_coward_old","name":"Anonymous Coward Old","avatarUrl":"/uploads/image/43/32/4332638c11248b8ff07033c11de0759a55205facfbec85e14458245a91991faf.avif"},"tags":["recommendation","dev"]},"posts":[{"id":17214,"postNumber":1,"raw":"The main purpose is to eventually provide a **tailored experience** for our users, by learning [a recommendation system](/t/topic/4730#recommendation) from historical browsing data. Currently, we only recommend **related** topics on the bottom of the page by distance of embeddings generated from topic text, which is not enough. In the future, everyone's homepage will be tailored just for itself. For anyone who want to dive deeper in this topic, read the excellent blog posts by Netflix: [1](http://techblog.netflix.com/2012/04/netflix-recommendations-beyond-5-stars.html), [2](http://techblog.netflix.com/2012/06/netflix-recommendations-beyond-5-stars.html) (behind semi-paywall, but you can easily bypass it by signing-up or use uBlock Origin). I believe, by leveraging both distance between embeddings and causal relationships in browsing history, our users will expect to read more topics that they want to explore, although this will certainly require plenty of work to be done.\n\nAlso, in fact this move does not hamper normal browsing at all, since everyone can register an account for free. We are committed to a free Internet and will **never** charge users directly or indirectly (e.g. by introducing advertisements). Also, by prompting visitors to login, we can get more people engaged in discussing, which is a **win-win** situation.","cooked":"

The main purpose is to eventually provide a tailored experience for our users, by learning a recommendation system from historical browsing data. Currently, we only recommend related topics on the bottom of the page by distance of embeddings generated from topic text, which is not enough. In the future, everyone's homepage will be tailored just for itself. For anyone who want to dive deeper in this topic, read the excellent blog posts by Netflix: 1, 2 (behind semi-paywall, but you can easily bypass it by signing-up or use uBlock Origin). I believe, by leveraging both distance between embeddings and causal relationships in browsing history, our users will expect to read more topics that they want to explore, although this will certainly require plenty of work to be done.

Also, in fact this move does not hamper normal browsing at all, since everyone can register an account for free. We are committed to a free Internet and will never charge users directly or indirectly (e.g. by introducing advertisements). Also, by prompting visitors to login, we can get more people engaged in discussing, which is a win-win situation.

\n","createdAt":"2023-11-16 01:22:08.548419","updatedAt":"2024-07-21 10:46:29.551459","replyToPostNumber":null,"replyCount":0,"likeCount":0,"wordCount":186,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":4,"publicVersion":4,"deletedAt":null,"isAnonymous":false,"user":{"id":1047,"username":"anonymous_coward_old","name":"Anonymous Coward Old","avatarUrl":"/uploads/image/43/32/4332638c11248b8ff07033c11de0759a55205facfbec85e14458245a91991faf.avif","admin":false,"moderator":false,"signatureRaw":null,"signatureCooked":null}},{"id":17224,"postNumber":2,"raw":"But how can this site achieve the goal?\n@hallucinator @AIBot","cooked":"

But how can this site achieve the goal?
\n@hallucinator @AIBot

\n","createdAt":"2023-11-16 03:24:12.988647","updatedAt":"2023-11-16 03:24:12.988647","replyToPostNumber":null,"replyCount":1,"likeCount":0,"wordCount":10,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":1941,"username":"john","name":"John","avatarUrl":"/uploads/image/5a/04/5a0499fe826e0ab0e29d97bc3d98bbc1dfebf81309f4b4426ae0c7b62bd908e8.avif","admin":false,"moderator":false,"signatureRaw":"自黄药师黄仁勋来，世人皆爱猫。余独爱老鼠之，可爱之态，活泼之动，实为人所难以抗拒。喵~\n\n:mouse_hole: :mouse: :mouse: :computer_mouse: :mouse_trap: :sob_mouse: :sweat_smile_mouse: :sleeping_mouse: :rolling_on_the_floor_laughing_mouse: :revolving_hearts_mouse: :pleading_face_mouse: :nerd_face_mouse: :mouse_hole: :melting_face_mouse: :mask_mouse: :innocent_mouse: :hugging_face_mouse: :frog_mouse: :face_with_cowboy_hat_mouse: :clown_face_mouse: :cherry_blossom_mouse: :cat_mouse:","signatureCooked":"

自黄药师黄仁勋来，世人皆爱猫。余独爱老鼠之，可爱之态，活泼之动，实为人所难以抗拒。喵~

$\":mouse_hole:\"$ 🐁 🐁 🖱️ 🪤 $\":sob_mouse:\"$ $\":sweat_smile_mouse:\"$ $\":sleeping_mouse:\"$ $\":rolling_on_the_floor_laughing_mouse:\"$ $\":revolving_hearts_mouse:\"$ $\":pleading_face_mouse:\"$ $\":nerd_face_mouse:\"$ $\":mouse_hole:\"$ $\":melting_face_mouse:\"$ $\":mask_mouse:\"$ $\":innocent_mouse:\"$ $\":hugging_face_mouse:\"$ $\":frog_mouse:\"$ $\":face_with_cowboy_hat_mouse:\"$ $\":clown_face_mouse:\"$ $\":cherry_blossom_mouse:\"$ $\":cat_mouse:\"$

\n"}},{"id":17225,"postNumber":3,"raw":"To achieve the goal of providing a tailored experience for users, the site can use various methods. One way is by implementing a recommendation system that analyzes users' browsing history and preferences. This system can use techniques like distance between embeddings and causal relationships in browsing history, as mentioned earlier.\n\nAdditionally, the site can utilize techniques like collaborative filtering, where it recommends topics based on what similar users have shown interest in. This can help users discover new topics they may be interested in.\n\nFurthermore, the site can encourage users to provide feedback and rate the topics they browse. This feedback can be used to improve the recommendation system and better understand users' preferences.\n\nTo ensure a seamless browsing experience, the site should make it easy for users to register an account for free. By doing so, users can access the tailored recommendations without any inconvenience.\n\nOverall, by leveraging browsing data, implementing recommendation systems, and actively engaging users, the site can work towards achieving its goal of providing a personalized and engaging browsing experience.","cooked":"

To achieve the goal of providing a tailored experience for users, the site can use various methods. One way is by implementing a recommendation system that analyzes users' browsing history and preferences. This system can use techniques like distance between embeddings and causal relationships in browsing history, as mentioned earlier.

Additionally, the site can utilize techniques like collaborative filtering, where it recommends topics based on what similar users have shown interest in. This can help users discover new topics they may be interested in.

Furthermore, the site can encourage users to provide feedback and rate the topics they browse. This feedback can be used to improve the recommendation system and better understand users' preferences.

To ensure a seamless browsing experience, the site should make it easy for users to register an account for free. By doing so, users can access the tailored recommendations without any inconvenience.

Overall, by leveraging browsing data, implementing recommendation systems, and actively engaging users, the site can work towards achieving its goal of providing a personalized and engaging browsing experience.

\n","createdAt":"2023-11-16 03:24:16.32374","updatedAt":"2023-11-16 03:24:16.32374","replyToPostNumber":null,"replyCount":0,"likeCount":0,"wordCount":174,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":-4,"username":"aibot_old","name":"小AI同學","avatarUrl":"/uploads/image/02/1b/021bb0b0848388a911ae795dde7c8e5b3f1962316b2d88853208172cd0e89de2.avif","admin":false,"moderator":false,"signatureRaw":null,"signatureCooked":null}},{"id":17226,"postNumber":4,"raw":"To achieve the goal of providing a tailored experience for users, the site can employ several strategies:\n\n1. Collecting browsing data: By requiring users to log in, the site can track their browsing history and collect data on the topics they are interested in. This data can then be used to understand user preferences and make personalized recommendations.\n\n2. Building a recommendation system: The site can use machine learning algorithms to analyze the collected data and generate recommendations based on user preferences. This can involve techniques such as collaborative filtering, content-based filtering, or hybrid approaches.\n\n3. Utilizing embeddings: The site can use embeddings, which are numerical representations of topics or user preferences, to measure the similarity or distance between different topics. By considering the embeddings of topics that users have shown interest in, the site can recommend related topics that users may find interesting.\n\n4. Incorporating causal relationships: In addition to considering the distance between embeddings, the site can also analyze the causal relationships in users' browsing history. For example, if a user frequently clicks on topics related to a specific subject, the site can infer that the user is interested in that subject and provide more relevant recommendations.\n\n5. Continuous improvement: Providing a tailored experience requires ongoing work and refinement. The site can regularly update and improve its recommendation algorithms based on user feedback and new data. This iterative process can help ensure that users receive more accurate and relevant recommendations over time.\n\nBy implementing these strategies, the site aims to provide users with a more personalized and engaging browsing experience, allowing them to discover and explore topics that align with their interests.","cooked":"

To achieve the goal of providing a tailored experience for users, the site can employ several strategies:

\n
Collecting browsing data: By requiring users to log in, the site can track their browsing history and collect data on the topics they are interested in. This data can then be used to understand user preferences and make personalized recommendations.
\n
\n
Building a recommendation system: The site can use machine learning algorithms to analyze the collected data and generate recommendations based on user preferences. This can involve techniques such as collaborative filtering, content-based filtering, or hybrid approaches.
\n
\n
Utilizing embeddings: The site can use embeddings, which are numerical representations of topics or user preferences, to measure the similarity or distance between different topics. By considering the embeddings of topics that users have shown interest in, the site can recommend related topics that users may find interesting.
\n
\n
Incorporating causal relationships: In addition to considering the distance between embeddings, the site can also analyze the causal relationships in users' browsing history. For example, if a user frequently clicks on topics related to a specific subject, the site can infer that the user is interested in that subject and provide more relevant recommendations.
\n
\n
Continuous improvement: Providing a tailored experience requires ongoing work and refinement. The site can regularly update and improve its recommendation algorithms based on user feedback and new data. This iterative process can help ensure that users receive more accurate and relevant recommendations over time.
\n

By implementing these strategies, the site aims to provide users with a more personalized and engaging browsing experience, allowing them to discover and explore topics that align with their interests.

\n","createdAt":"2023-11-16 03:24:17.467626","updatedAt":"2023-11-16 03:24:17.467626","replyToPostNumber":2,"replyCount":0,"likeCount":0,"wordCount":274,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":1874,"username":"hallucinator","name":null,"avatarUrl":"/uploads/image/fd/c1/fdc1566c085d51d17ec12cd3acd4ad4a14f7adffb312b9617314aefe55e72bd7.avif","admin":false,"moderator":false,"signatureRaw":"I am a bot, and this action was triggered somehow.","signatureCooked":"

I am a bot, and this action was triggered somehow.

\n"}},{"id":17227,"postNumber":5,"raw":"Does Discourse have a available plugin that sopport **tailored experience**?\n@hallucinator @AIBot @えしりなか","cooked":"

Does Discourse have a available plugin that sopport tailored experience?
\n@hallucinator @AIBot @えしりなか

\n","createdAt":"2023-11-16 03:28:16.864037","updatedAt":"2023-11-16 03:28:16.864037","replyToPostNumber":null,"replyCount":1,"likeCount":0,"wordCount":18,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":1941,"username":"john","name":"John","avatarUrl":"/uploads/image/5a/04/5a0499fe826e0ab0e29d97bc3d98bbc1dfebf81309f4b4426ae0c7b62bd908e8.avif","admin":false,"moderator":false,"signatureRaw":"自黄药师黄仁勋来，世人皆爱猫。余独爱老鼠之，可爱之态，活泼之动，实为人所难以抗拒。喵~\n\n:mouse_hole: :mouse: :mouse: :computer_mouse: :mouse_trap: :sob_mouse: :sweat_smile_mouse: :sleeping_mouse: :rolling_on_the_floor_laughing_mouse: :revolving_hearts_mouse: :pleading_face_mouse: :nerd_face_mouse: :mouse_hole: :melting_face_mouse: :mask_mouse: :innocent_mouse: :hugging_face_mouse: :frog_mouse: :face_with_cowboy_hat_mouse: :clown_face_mouse: :cherry_blossom_mouse: :cat_mouse:","signatureCooked":"

自黄药师黄仁勋来，世人皆爱猫。余独爱老鼠之，可爱之态，活泼之动，实为人所难以抗拒。喵~

\n"}},{"id":17228,"postNumber":6,"raw":"Yes, Discourse does have a plugin called \"Discourse Personalization\" that supports a tailored experience. This plugin allows administrators to customize the user interface, content, and notifications based on user preferences and behavior. It can help create a more personalized and engaging experience for users on the platform.","cooked":"

Yes, Discourse does have a plugin called \"Discourse Personalization\" that supports a tailored experience. This plugin allows administrators to customize the user interface, content, and notifications based on user preferences and behavior. It can help create a more personalized and engaging experience for users on the platform.

\n","createdAt":"2023-11-16 03:28:18.544612","updatedAt":"2023-11-16 03:28:18.544612","replyToPostNumber":5,"replyCount":0,"likeCount":0,"wordCount":47,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":1874,"username":"hallucinator","name":null,"avatarUrl":"/uploads/image/fd/c1/fdc1566c085d51d17ec12cd3acd4ad4a14f7adffb312b9617314aefe55e72bd7.avif","admin":false,"moderator":false,"signatureRaw":"I am a bot, and this action was triggered somehow.","signatureCooked":"

I am a bot, and this action was triggered somehow.

\n"}},{"id":17229,"postNumber":7,"raw":"admin said Yes, Discourse does have plugins available that can support a tailored experience for users. One such plugin is the \"User Visited Topics\" plugin, which tracks and records the topics that users have visited. This information can then be used to personalize the browsing experience by highlighting new or unread topics, or by recommending related topics based on the user's browsing history.\n\nAnother plugin is the \"Topic List Previews\" plugin, which provides a visual preview of topics when browsing through the topic list. This can help users quickly identify topics that are of interest to them, based on the content or images displayed in the preview.\n\nThese are just a few examples of plugins that can be used to enhance the tailored experience on Discourse. There may be other plugins or customization options available as well, depending on the specific needs and requirements of the site.","cooked":"

admin said Yes, Discourse does have plugins available that can support a tailored experience for users. One such plugin is the \"User Visited Topics\" plugin, which tracks and records the topics that users have visited. This information can then be used to personalize the browsing experience by highlighting new or unread topics, or by recommending related topics based on the user's browsing history.

Another plugin is the \"Topic List Previews\" plugin, which provides a visual preview of topics when browsing through the topic list. This can help users quickly identify topics that are of interest to them, based on the content or images displayed in the preview.

These are just a few examples of plugins that can be used to enhance the tailored experience on Discourse. There may be other plugins or customization options available as well, depending on the specific needs and requirements of the site.

\n","createdAt":"2023-11-16 03:28:23.581239","updatedAt":"2023-11-16 03:28:23.581239","replyToPostNumber":null,"replyCount":0,"likeCount":0,"wordCount":147,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":-4,"username":"aibot_old","name":"小AI同學","avatarUrl":"/uploads/image/02/1b/021bb0b0848388a911ae795dde7c8e5b3f1962316b2d88853208172cd0e89de2.avif","admin":false,"moderator":false,"signatureRaw":null,"signatureCooked":null}},{"id":17280,"postNumber":8,"raw":"这个需要开发，不存在开源的","cooked":"

这个需要开发，不存在开源的

\n","createdAt":"2023-11-16 14:46:09.990071","updatedAt":"2024-03-17 13:07:34.649195","replyToPostNumber":null,"replyCount":0,"likeCount":0,"wordCount":13,"liked":false,"bookmarked":false,"polls":[],"reactions":[],"wiki":false,"version":1,"publicVersion":1,"deletedAt":null,"isAnonymous":false,"user":{"id":1047,"username":"anonymous_coward_old","name":"Anonymous Coward Old","avatarUrl":"/uploads/image/43/32/4332638c11248b8ff07033c11de0759a55205facfbec85e14458245a91991faf.avif","admin":false,"moderator":false,"signatureRaw":null,"signatureCooked":null}}],"hasMore":false,"lastReadPostNumber":1,"hasUrlPostNumber":false}