[Elsnet-list] 2nd Call for Participation for the IGGSA Shared Task on German Sentiment Analysis

Josef Ruppenhofer ruppenho at uni-hildesheim.de
Wed Jun 11 19:23:51 CEST 2014

Dear list members,

We are pleased to announce the IGGSA (Interest Group on German Sentiment 
Analysis) Shared Task on German Sentiment Analysis. It is open to any 
interested participants from both academia and industry.


Sentiment analysis and opinion mining have received increasing attention 
both in the scientific community as well as in industry. Use cases 
include the analysis of products, marketing campaigns, brands, 
companies, political speeches and more. However, most work has been 
performed on the English language. With this shared task, we put a focus 
on German. We offer fine-grained analysis tasks in two different 
domains: political speeches on the one hand, and product reviews on the 

The shared task consists of two main tasks:

Sentiment Analysis on German speeches from the Swiss parliament

_Full task_
Identification of subjective expressions with source and targets.

_Subtask 1a_
Subjective expressions are given, the task is to identify opinion sources.

_Subtask 1b_
Subjective expressions are given, the task is to identify the opinion 

Cross-Domain Sentiment Analysis on German product reviews from Amazon.

_Subtask 2a_
Identify subjective phrases.

_Subtask 2b_
Identify aspect phrases.

_Subtask 2c_
Identify subjective phrases and aspect phrases and indicate for each 
aspect phrase which subjective phrase it is the target of (if any).

More detailed information can be found at 


All tasks are evaluated on unseen test data. For main task 1, the data 
set consists of 600 sentences representing continuous segments of 25 
speeches on 9 different topics given before the Swiss parliament. For 
main task 2, the test data will be in the same format as the USAGE data 
set, which serves as training data (it consists of annotations for more 
than 600 reviews, http://dx.doi.org/10.4119/unibi/citec.2014.14). The 
test data will be from a different household product category than the 
ones included in the USAGE data set.

Trial data are already available for both main tasks.
For main task 2, the full training data is available, too.


_Main Task 1_
August 1st, 2014: Release of evaluation data for main subtask
August 10th, 2014: Submission of results (max. 5 runs) for full task
August 11th, 2014: Release of data for subtask a and b
August 21st, 2014: Submission of results (max. 5 runs) for subtask a and b
September 1st, 2014: Report results to each team individually

_Main Task 2_
August 11st, 2014: Release of evaluation data for all subtasks.
August 21th, 2014: Submission of results (max. 5 runs)
September 1st, 2014: Report results to each team individually

_Both Main Tasks_
July 15th, 2014: Registration deadline
September 22nd, 2014: Working note submission
Camera ready papers are to be submitted after the workshop, by
October 30th, 2014. Papers will be published online alongside the papers 
of other KONVENS workshops.


July 15th, 2014: Registration deadline

Please register at: 

Every participant is strongly encouraged to also register on our mailing 
list at: 


The workshop for the shared task will take place in Hildesheim/Germany 
on October 7th, 2014, one day prior to the beginning of the KONVENS 
conference, which the workshop is co-located with. 

Participants are asked to register for the main conference; the 
registration fee covers the main conference and all workshops.


Josef Ruppenhofer (Uni Hildesheim)
Jonathan Sonntag (Uni Potsdam)
Julia Maria Struss (Uni Hildesheim)
Michael Wiegand (Uni Saarland)
Roman Klinger (Uni Bielefeld)


You can contact the organizers via the email address 
iggsa-gestalt-coordinators at googlegroups.com. In addition, we maintain a 
mailing list at 
for exchange between participants and organizers. We strongly encourage 
you to register on this list when you are interested in participation.


We are happy to acknowledge the financial support that the GSCL (German 
Society of Computational Linguistics) has granted us for annotating task 
1 data. Task 2 has been supported by the BMBF project It’s OWL 

More information about the Elsnet-list mailing list