#Microposts2016: 6th Workshop on Making Sense of Microposts: Big things come in small packages

  title={\#Microposts2016: 6th Workshop on Making Sense of Microposts: Big things come in small packages},
  author={Amparo Elizabeth Cano and Daniel Preotiuc-Pietro and Danica Radovanovi{\'c} and Katrin Weller and Aba-Sah Dadzie},
  journal={Proceedings of the 25th International Conference Companion on World Wide Web},
Amparo E. Cano∗ Kmi, The Open University / Aston Business School, UK amparo.cano@open.ac.uk Daniel Preoţiuc-Pietro University of Pennsylvania Philadelphia, USA danielpr@sas.upenn.edu Danica Radovanović University of Novi Sad Novi Sad, Serbia danica@danicar.org Katrin Weller GESIS Leibniz Institute for the Social Sciences, Germany katrin.weller@gesis.org Aba-Sah Dadzie KMi, The Open University Milton Keynes, UK aba-sah.dadzie@open.ac.uk 

REDES at TAC Knowledge Base Population 2016 : EDL and BeSt tracks

A description of the Entity Linking system known as REDES, which was involved into the track Entity Discovery and Linking (EDL) of the challenge TAC Knowledge Base Population (KBP) 2016, and a model based on Bayesian programing is proposed.

Better together: an ensemble learner for combining the results of ready-made entity linking systems

A supervised approach is introduced which exploits the output of multiple ready-made EL systems by predicting the correct link on a per-mention basis and has the capacity to significantly outperform the individual EL systems as well as a set of baseline methods.

Temporally-Informed Analysis of Named Entity Recognition

This work analyzes and proposes methods that make better use of temporally-diverse training data, with a focus on the task of named entity recognition, and empirically demonstrates the effect of temporal drift on performance and how the temporal information of documents can be used to obtain better models compared to those that disregard temporal information.

Truth Assessment of Objective Facts Extracted from Tweets: A Case Study on World Cup 2014 Game Facts

This paper shows that the truth of a tweet can be determined by using a statistical classifier supported by an architecture of three preprocessing phases and it is shown that the Tweets which contain one or more false facts are determined.

Feature-Rich Twitter Named Entity Recognition and Classification

This paper introduces a Twitter named entity system using a supervised machine learning approach, namely Conditional Random Fields, which obtained the second highest F1 score in the shared task: 63.22%.

A Feature-based Ensemble Approach to Recognition of Emerging and Rare Named Entities

5-fold cross-validation based on training and development data for the emerging and rare named entity recognition shared task showed precision, recall and F1-score of 66.87%, 46.75% and 54.97%, respectively.

Over a Decade of Social Opinion Mining

A thorough systematic review was carried out on Social Opinion Mining research, tasked with the identification of multiple opinion dimensions, such as subjectivity, sentiment polarity, emotion, affect, sarcasm and irony, from user-generated content represented across multiple social media platforms and in various media formats.

Long distance history influences sentence valence in narrative texts

This work shows that there is a small linear relationship between sentence valence history and the valence of the current sentence, which is statistically significant and intends to explore the application of models with non-linear capabilities in future work.