Thomas Steiner presents "Summarizing Events with Social Media"
We have invited Thomas Steiner from Google to speak to us about Summarizing Events with Social Media. Followed by a healthy Q & A.
- 7:00 pm: meet, greet & eat
- 7:15 pm: intros
- 7:30 pm: main presentation
- Q&A after the talk
Smartphones, tablets, or digital cameras together with social networks enable people to create, share, and consume enormous amounts of media items like videos or photos. Mobile devices are omnipresent at all sorts of events, where, given a stable network connection, part of the event-related media items are published on social networks, both as the event happens, or afterwards, once a stable network connection has been re-established. Our research question is: "Can user-customizable media galleries that summarize given events be created solely based on textual and multimedia data from social networks”? We have developed and evaluated an application and related methods for media item enrichment, leveraging social networks, utilizing the Web of Data, techniques known from Content-based Image Retrieval (CBIR) and Content-based Video Retrieval (CBVR), and fine-grained media item addressing schemes like Media Fragments URIs, to provide a scalable and near real-time solution to realize event summarization and media item compilation.
For any event with given event title(s), (potentially vague) event location(s), and (arbitrarily fine-grained) event date(s), our approach can be divided in the following six steps.
- Via the textual search functionality of different social networks, we retrieve a list of potentially event-relevant microposts that either contain media items directly, or that provide links to media items on external media item hosting platforms.
- Using third-party Natural Language Processing (NLP) tools, we recognize and disambiguate named entities in the microposts to predetermine their relevance.
- We extract the binary media item data from social networks or media item hosting platforms and relate it to the originating microposts.
- Using CBIR and CBVR techniques, we first deduplicate exact and near-duplicate media items, and then cluster similar media items.
- We rank the deduplicated and clustered list of media items and their related microposts according to well-defined ranking criteria.
- In order to generate interactive and user-customizable media galleries that visually and audibly summarize the event in question, we compile the top-n ranked media items and microposts in an aesthetic way.
Thomas Steiner is a proud dad-of-three, a Research Scientist at Google, and a PhD student at UPC.edu. His main research interests these days are the Semantic Web, Linked Data, and the architectural style REST. He holds two Master of Computer Science degrees, one from the Technical University of Karlsruhe, Germany, and the other from the École Nationale Supérieure d'Informatique et de Mathématiques Appliquées de Grenoble, France. In addition to that he works on making the Internet a better place.
You can find Thomas at:
Google's mission is to organize the world's information and make it universally accessible and useful. Our company has packed a lot into a relatively young life. Since Google was founded in 1998, we’ve grown to serve hundreds of thousands of users and customers around the world.
FOOD & BEVERAGE
Food and beverages will be provided, so we don't listen to a great talk on an empty stomach :)
If you need a ride or can offer a ride, please post a comment underneath this meetup
Street Parking is usually readily available, most of the meters are free after 6pm. Please check the street signs as some sides of the streets are permit parking only.
Want to hear about upcoming meetups? Follow us on Twitter!