Conf: EACL 2014 Tutorial in Natural Language Processing for Social Media

Thierry Hamon hamon at LIMSI.FR
Fri Mar 7 20:36:16 UTC 2014

Date: Wed, 5 Mar 2014 11:32:47 +0100
From: peter ljunglöf <peter.ljunglof at>
Message-Id: <5B733E16-5291-44CC-BFFB-95DADA4136A1 at>


   EACL Tutorial in Natural Language Processing for Social Media

   Gothenburg, Sweden, 26 April 2014

There is an increasing need to interpret and act upon information from
large-volume, social media streams, such as Twitter, Facebook, and forum
posts. However, NLP methods face difficulties when processing social
media text. We call for participation in an intermediate-to-advanced
level tutorial, discussing the state of the art in processing social
media text.

Key points of the tutorial include:
- Characterisation of language in social media, and why it is difficult
  to process
- In-depth examination of multiple approaches to core NLP tasks on
  social media text
- Discussion of corpus collection and the use of crowdsourcing for
- Practical, legal and ethical aspects of gathering and distributing
  social media data and metadata
- Current and future applications of social media information

The tutorial takes a detailed view of key NLP tasks (corpus annotation,
linguistic pre-processing, information extraction and opinion mining) of
social media content. After a short introduction to the challenges of
processing social media, we will cover key NLP algorithms adapted to
processing such content, discuss available evaluation datasets and
outline remaining challenges.

The core of the tutorial will present NLP techniques tailored to social
media, specifically: language identification, tokenisation,
normalisation, part-of-speech tagging, named entity recognition, entity
linking, event recognition, opinion mining, and text summarisation.

Since the lack of human-annotated NLP corpora of social media content is
another major challenge, this tutorial will cover also crowdsourcing
approaches used to collect training and evaluation data (including
paid-for crowdsourcing with CrowdFlower, also combined with
expert-sourcing and games with a purpose). We will also discuss briefly
practical and ethical considerations, arising from gathering and mining
social media content.

The last part of the tutorial will address applications, including
summarisation of social media content, user modelling (geo-location,
age, gender, and personality identification), media monitoring and
information visualisation (for e.g. detecting bushfires, predicting
virus outbreaks), and using social media to predict economical and
political outcomes (e.g. stock price movements, voting intentions).

  Web address:

Registration is to be made online via the EACL main registration site:

This tutorial is supported by the CHIST-ERA project uComp (
and also by the EU FP7 project Pheme (

Hope to see you in Göteborg!

Leon Derczynski and Kalina Bontcheva

Message diffuse par la liste Langage Naturel <LN at>
Informations, abonnement :
English version       : 
Archives                 :

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  :

ATALA décline toute responsabilité concernant le contenu des
messages diffusés sur la liste LN

More information about the Ln mailing list