For the past two years, social media platforms have been rolling out machine translation, enabling multilingual interactions. However, the people interacting in these platforms often know each other already, and have a language in common (i.e., friends). But what happens when machine translation is used to facilitate interactions among strangers, who perhaps have common interests but not a common language?
The earliest social media platform to enable machine translation was probably Facebook, which began autotranslating conversations in Facebook pages (a good place to start given that Pages are more likely to bring people who speak different languages together). Likewise, Google+ and Twitter later released similar features, enabling, for example, Spanish-speaking Twitter users to read the tweets from the now toppled Egyptian president Muhammad Morsi, translated from Arabic to Spanish:
How often do these types of multilingual interactions occur? Ethan Zuckerman posed a similar question when wondering what the numbers were for machine translations, in the context of a discussion about the challenges of having people pay attention to content outside their immediate reach.
With that in mind, we decided to look into some numbers using data from our own social media platform: Socl, which started offering machine translation since last year. Socl, like Twitter, often brings strangers together who might not speak the same language, example:
[Talk] Computational Sociology—Digital Traces in Online Places: Methods, Software, & Applications—Thu 10/35 months ago - permalink
This coming Thursday, Ryan Acton, a computational sociology professor at UMass Amherst, is coming to give a talk on his work investigating “digital traces” online. Ryan has been studying network dynamics on websites such as epinions.com, and last.fm. For example, he’s been analyzing group formation around concerts advertised in last.fm and built an R package called scrapeR to collect data directly from R.
FUSE Labs, in collaboration with the iConference, is offering a $3,000 travel award for each team selected to participate in the 2014 Social Media Expo in Berlin. Teams must be from one of the member institutions. More info here.
The teams need to submit a 4-page paper along with a video, that incorporate user research, design, prototyping, and/or system evaluation around topics such as:
- Collecting and evaluating big social data
- Statistical/algorithmic work for detecting and summarizing societal patterns
- Visualization of societal patterns
- Designing for large scale collective action
- Supporting emergent, community-based civic activities in addition to direct governmental involvement
The projects must explore a technological solution to meeting a concrete need or opportunity around the theme of leveraging social media to foster a smarter society.
UPDATE: Video of this presentation is now available online.
Next week we have Alex Schulz from the Technical University of Darmstadt who will giving a talk about his work on using social media data along with machine learning, and semantic dictionaries (i.e., WordNet), to automatically detect small scale incidents, such as car crashes, shootings, and fires.
I saw Alex present a paper co-authored with Petar Ristoski at ICWSM during a really interesting workshop titled When the City Meets the Citizen. In that paper they analyzed Twitter data from Seattle and Memphis. One of their findings was that average citizens (labeled I and blue in the figure below) were often the first to report shootings (53% of the time), much earlier than other people that one would expect such as Emergency Management Organzations (EMO), journalists/bloggers devoted to emergencies (EMJ), general journalists/bloggers, or other types of governmental and non-governmental organizations (ORG).
Along with my colleagues Shelly Farnham, and Michal Lahav—and our interns Yuheng Hu, Emma Spiro, and Nate Matias—we have been exploring ways of discovering and fostering latent neighborhood information to help people understand what’s happening in their local communities.
As part of this research, we have created Whooly an experimental mobile website that discovers and highlights neighborhood-specific information on Twitter in real-time. The system is focused, for now, on various neighborhoods of the Seattle metro area (King County to be specific). Whooly automatically discovers, extracts and summarizes hyperlocal Twitter content from these communities based on mentions of local neighborhoods and relevant keywords from tweets and profiles. One can think of Whooly as a neighborhood Twitter client.
Screenshot of Whooly
Talk Announcement — Narrating with Networks: Making Sense of Event Log Data with Socio-Technical Trajectories — Fri 8/166 months ago - permalink
Breaking news events are in red, articles about recent but non-breaking news events are in blue, and articles about historical events are in green. The x-axis is time and the y-axis is the number of articles in the giant component.
- The Tiny Icon Factory is a tool and gallery for the anonymous creation of black and white low resolution icons. With over 200,000 anonymous and uncensored contributions in under two years, The Tiny Icon Factory is an ongoing exploration of creative expression.
- PictureXS was an anonymous picture aggregator. It featured an embedded tracing tool, a self-regulated censorship system, and tags. Before it was turned off in January 2011, PictureXS had collected over 30,000 pictures, 1000 drawings and 500,000 tags, reporting activity from across the world.
- OpenStudio (2005 to 2008) was a pioneering experiment in creativity, collaboration & commerce. Participants created and sold artwork in an online marketplace using an embedded drawing tool and virtual currency.
How can we create designs that help us overcome the biases in our awareness of news? Today at Microsoft Research, Elena Agapie talked about political memes and her user interface experiments to measure user bias in what we click. These biases in behaviour sometimes get reinforced by our computer systems to form what Eli Pariser calls The Filter Bubble.
I first got to know Elena during her MS in computer science at Harvard University. Her work in the last few years has focused on:
- user interfaces for behavior change (Harvard)
- news and participatory media (in collaboration with the MIT Center for Civic Media)
- news aggregation and analysis (in collaboration with the Berkman Center)
- interactive datavisualization (currently at the NASA Jet Propulsion Lab)
(today we had the Microsoft Design Expo. These livenotes are a raw, as-it-happened record of the presentations)
We live in a world alive with sensors and data. The big data, sensor networks and transparency movements have left us with a supply-side glut of potential useful free data that is lying fallow. How can we use this to improve life, local community and the world at large? Today, the Microsoft Design Expo, part of the annual Faculty Summit, showcased projects along this theme from design students at:
- Technische Universiteit (TU) Eindhoven
- Carnegie Mellon University
- National Institute of Design
- Universidad Iberoamericana, Design Department
- Northumbria University
- UCLA, Design Media Arts,
- New York University, Interactive Telecommunications Program
- Interdisciplinary Center (IDC)