Skip to main content

Sound Index

Intelligent Information Systems project : BBC Sound Index

The music ratings industry has not changed in the last 50 years, despite the advent of emerging ways to access media. The internet and the popularity of online music are pushing companies to re-evaluate prevailing models for constructing ratings. This is a pioneering project to tap into the online buzz surrounding artists and songs, by leveraging several popular sources.

The BBC Sound Index is a catalogue of the hottest artists and tracks that are currently being talked about on the internet. The technology powering the BBC Sound Index has been developed at the IBM Almaden Research Center in California, US and is called MONGOOSE. MONGOOSE leverages lessons from the Semantic Super Computing (SSC) effort. A variety of content ingestion techniques are employed to continuously gather user comments, listens, views and other interest indicators across multiple sources on the internet. This content is then processed through an analytics chain, which is comprised of advanced linguistic and natural language processing (NLP) technology. Comments are transliterated, de-spammed, and analyzed for relevance, and listens and views are aggregated at the band and individual track level. Client-supplied algorithms are used to generate a ranked list of bands and tracks. The more mentions, posts, plays and views an artist or track has, the higher it will be on the SoundIndex. Thus, the SoundIndex charts are completely controlled by the public. The data collected is completely anonymized, and no user information is exposed via the BBC Sound Index.

In a nutshell, the system continuously crawls and ingests content, aggregates track and artist rankings and provides the result via a user-friendly interface.

Team: Alfredo Alba, Varun Bhagwan, Tyrone Grandison, Daniel Gruhl, Jan Pieper.

Links

Presentations

  • BBC Sound Index - Music Charts for the 21st Century. IBM Talk. (Slide Deck)

  • Accelerating Advances in Text Analytics. KeyNote Speech at Language Resources and Evaluation (LREC) 2008. (Slide Deck)

Papers

  1. Daniel Gruhl, Meena Nagarajan, Jan Pieper, Christine Robson, Amit Sheth. "Context and Domain Knowledge Enhanced Entity Spotting in Informal Text". To appear in the Proceedings of the 8th International Semantic Web Conference (ISWC) 2009. Fairfax, Virginia, USA. October 2009.

  2. Varun Bhagwan, Tyrone Grandison, Alfredo Alba, Daniel Gruhl, Jan Pieper. "MONGOOSE: MONitoring Global Online Opinions via Semantic Extraction". To appear in 2009 Service Quality and Assurance Management (SQAM) workshop at IEEE 2009 International Conference on Cloud Computing (CLOUD-II 2009), Bangalore, India, September 21-25, 2009.

  3. Varun Bhagwan, Tyrone Grandison, Daniel Gruhl, "Sound Index: Music Charts By The People, For The People". Communications of the ACM. September 2009. Vol 52, No 9.

  4. Alfredo Alba, Varun Bhagwan, Tyrone Grandison, Daniel Gruhl, Jan Pieper. "Change Detection and Correction Facilitation for Web Applications and Services". The Proceedings of the 7th IEEE International Conference on Web Services (ICWS 2009). Los Angeles, CA, USA. July 2009.

  5. Varun Bhagwan, Tyrone Grandison. "Deactivation of Unwelcomed Deep Web Extraction Services through Random Injection". The Proceedings of the 7th IEEE International Conference on Web Services (ICWS 2009). Los Angeles, CA, USA. July 2009.

  6. Tyrone Grandison, Daniel Gruhl. "Turning Web X.0 Data Into Competitive Advantage". The First Caribbean Conference on Information and Communications Technology (CCICT 2009). Kingston, Jamaica. March 2009.

  7. Alfredo Alba, Varun Bhagwan, Tyrone Grandison. "Accessing The Deep Web: When Good Ideas Go Bad". To appear in the Proceedings of the ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA). Nashville, Tennessee. October 2008.

  8. Alfredo Alba, Varun Bhagwan, Tyrone Grandison, Daniel Gruhl, Jan Pieper, "Text Analytics and Integration of Web 2.0 Sources to Transform Media & Entertainment". Information On Demand (IOD). Las Vegas, Nevada. October 2008.

  9. Alfredo Alba, Varun Bhagwan, Julia Grace, Daniel Gruhl, Kevin Haas, Meenakshi Nagarajan, Jan Pieper, Christine Robson, Nachiketa Sahoo. "Applications of Voting Theory to Information Mashups". Second IEEE International Conference on Semantic Computing. Santa Clara, CA, USA. Aug 2008.

Press