Theme: Making Sense of Microposts: Big things come in small packages
Microposts – "information published on the Web that is small in size and requires minimal effort to publish" – as a means for communication and exchanging information continues to increase in popularity and utility. Examples of Microposts include tweets (using plain text or with embedded links and objects); social network endorsement using, e.g., Instagram hearts; check-ins using, e.g., Facebook and Foursquare, pins on e.g., Pinterest; links to brief, pre-recorded and streaming video via Snapchat and Meerkat. Current development of apps for microblogging for the ubiquitous smartphone and other small, personal devices take advantage of built-in photo and video capture - these may accompany text or serve in themselves as the Micropost. Services such as those provided by WhatsApp, Viber, Snapchat, LINE and Saya, piggybacking on SMS/MMS and augmented with social media features, are therefore also growing in popularity, especially in emerging markets where the Internet is often accessible mainly via mobile networks. Such services now typically sync seamlessly with desktop or web front-ends, supporting seamless switching between devices. Microposts are also often used as a portal to other services, alerting users to, e.g., live video streams on Periscope and Meerkat.
Individual Microposts typically focus on a single thought, message or theme, often written on the go or in the moment, as events transpire. Microposts however collectively comprise a very large amount of heterogeneous data – a source of valued, collective intelligence about a range of topics, that may be mined for a variety of end uses, including opinion mining and crowd tracking, emergency response and community services. The #Microposts workshops aim to continue to provide a forum to enable discussion and hence, improve understanding of the social and cultural phenomena that influence the publication and reuse of Microposts; to assess different approaches to gleaning the information content of Micropost data; and discuss application of this knowledge content in a variety of contexts. Enabling the understanding and application of Microposts requires techniques and tools that function at scale, and that are able to handle the very high rate at which Microposts are published.
Despite advances in tools to tackle the specific challenges inherent to Micropost data, applications and approaches for analysing Microposts still rely on third party text extraction tools. Such tools are typically applied to extract entities and concepts contained in Microposts. An important aim of the workshop is to promote formal evaluation of the accuracy of text extraction tools specifically for Micropost data, as opposed to more typical comparative assessment using corpora of well-formed, normal length, natural language documents. To address this issue, starting with #MSM2013, the workshop hosted an entity extraction challenge in which participants detected named entities typed with corresponding concepts (e.g. 'Barack Obama' is a Person). In 2014, the challenge was extended to require also the linking of entities extracted to relevant DBpedia sources. 2015 saw further extension that tested the accuracy of entrants' systems in extracting entities and linking them with DBpedia, and also assessing the runtime efficiency of participants' systems. For #Microposts2016 we will consolidate the 2015 task and provide a base from which participants will deploy live systems. Evolution of the challenge each year addresses a current need of researchers and others who rely on the output of text extraction tools specifically built to support or adapted to Micropost data, and where reliability and computation time are important when dealing with large-scale datasets.
#Microposts2016 will focus on topics including, but not exclusive to, the three areas below:
|
|
A prize of £500, generously sponsored by MK:Smart, will be awarded to the best submission. |