Skip to main content

Herzbot: A prototype music recommender

Herzbot music recommender logo
Herzbot is a music recommender application on Facebook. This is the prototype:

Find Herzbot on Facebook.

The prototype uses a combination of collaborative filtering and a novel way to model social context I thought up to make music recommendations to you.

How does it work?


Herzbot constructs a profile for you and other Herzbot users. These profiles are then compared to give you recommendations from similar profiles. This is how ordinary collaborative filtering recommendations work. Herzbot also asks you for a few elite friends, which is your social context. This makes Herzbot unique. Your profile is constructed as follows:

  • You give Herzbot the name of one of your favourite artists and it gets a list of similar artists that you rate on a scale of 0 to 100%. Herzbot uses the Echo Nest API to get similar bands.

  • Then, you pick your elite friends who you think have more influence on your music taste than your ordinary Facebook contacts. Herzbot then constructs a profile for you. This is the only information Herzbot uses (user names and your band preferences and ratings that you dictate). I'm not browsing your profiles or spying on you or spamming email addresses. I'm not Santa Clause, although I would like to know where all the bad girls live.

  • Finally, when those friends also add the application, you get to see what they like and exactly how much. You also get recommendations straight from their listening profiles (that's the social context modelling part) or ordinary plain vanilla with a bit of flake recommendations (that's the collaborative filtering part, however your elite contacts still count a little bit more than ordinary Facebook users when it comes to making recommendations to you).


Can you listen to free music?


Yes! If you want to explore the recommended bands, you can find them on iLike with a link straight from Herzbot. iLike has quite an extensive database and you don't need to sign up to listen to streaming audio, which is why I chose iLike over Last.fm and the others where you need to join.

You can listen to your recommendations, listen to the top bands your friends like or listen to the entire profile of your elite friends. It is about exploring new music, after all.

Keep in touch


If you are on Facebook and you'd like to try it out, feel free to add it:

Add Herzbot, the socially conscious Facebook music recommender.

UPDATE: The questionnaire is now up and running. If you added Herzbot, please take the questionnaire (that's a survey for the Yanks):

The Herzbot Survey on Survey Monkey.

You are also welcome to join the developer's group and give me feedback:

Join the Herzbot developer's group.

If you add it, please check back daily over the course of the next two weeks. I will add a questionnaire, which I need to make my hairbrain scheme seem more plausible to academia. I would greatly appreciate your feedback! The other reason is that your recommendations will improve as your elite friends join and as more people join Herzbot.

Comments

Maddie said…
Hmm an interesting idea, not sure if I'd use it though as I already use Last.fm and quite like it. May give it a go though before totally dismissing it.
Garg the Unzola said…
Thanks for the comment!

The idea is not to make a replacement for Last.fm. Spotify is already a great replacement for Last.fm. This is merely a prototype to test a new way of getting music recommendations.

Music recommendations are bonus features with Last.fm, Spotify and iLike. The main feature of those sites is sharing your playlist with others. They make fairly reliable recommendations because they have a large database of users and artists, so they can fill in the gaps between similar profiles (ie they rely on collaborative filtering).

My facebook app is more modest and only aims to find ways to make recommendations without a large database of users and to model your social context. From my perspective, it works very well because I found new bands with only my elite friends added. From your perspective, it might not work this well. This is why I greatly appreciate any users I can get at this stage. I want it to work across the board and not just for me.
Jeanette said…
I think it is a great idea!!! Give it a shot :)

Popular posts from this blog

Fist bump the Trump

I must confess that I did not follow this election as it unfolded, because I have no skin in this game. I only became interested when I saw the crocodile tears on Facebook.

What fascinated me more was that the Trump supporters came out of the closet for the first time to voice their opinions. Virtually none of these Trump supporters espoused racist, misogynistic or any of those kind of deplorable views. Most of them were just pointing fingers at the know-it-all Clinton supporters.

What characterised this election? Rather than enlightened liberals waging a culture war with backward rednecks and hayseeds, three things characterised this election for me:
Shared hubris: Our candidate is bad, but the other candidate is even worse. Both parties seemed to espouse this sentiment.Joe Sixpack's Revenge: Based on voter turnout and based on for whom the largest voting group voted, this election was the revenge of the average American. That is average American by sheer number. Nobody bothered t…

Why has outrage come to dominate platforms like Twitter?

This question was posted on twitter by Sarah Britten Pillay. I shall try to answer that here, or at least address some of the topics surrounding this notion.

What makes a platform like Twitter more outrageous than the next? A brief summary of my thoughts on the topic: It would be interesting to contrive some outrage meter that could detect outrage levels in a piece of text.Plenty if not most of social media outrage is manufactured as a distraction.Outrage that isn't manufactured can be analysed by means of kin selection concepts from biology.If you aren't entirely sold on the sociobiology idea, then the balance of risk and incentive from game theory can also shed some light on the rationale behind social media outrage. Outrage levels are too damn high I do agree that social media platforms tend to be filled with more outrage than others, but as far as I know there is no means of detecting or measuring outrage. The need exists for some outrage quotient or some method of classify…

White tears the most valuable currency but not as valuable as fauxtrage

This formerly glorious publication which I shall not even bother naming has also fallen into the habit of censoring its comments section, at least when it comes to white tears. Fortunately, I could still save this obviously far superior comment from the rather myopic agitprop from whence it came. I know it is superior because the quality of your commentary is inversely proportional to how long it stays unscathed. That's why the sanctimonious finger-wagging op-eds rarely get deleted, but the comments rarely last long.
Anyone - black or white or of any other pigmentation persuasion - with a Rhodes Scholarship can but only cry White Tears. Someone with a Rhodes Scholarship is in the very lap of privilege, the likes of which not even the majority of pale South Africans born with a silver spoon will ever see. That is why it is not uncommon to see their ilk waiting on tables instead of whipping their slaves on their ill-begotten land, which they refuse to give up, you see.
A similar campa…