Program

SESSION 1 - PRESENTATIONS from 15:35 to 16:25 pm

We will have, in the reported order, the following nine presentations (5 minutes each)


Supporting programmers in naming identifiers
by Surafel Lemma Abebe and Paolo Tonella - SLIDES

Automated Source Code Comment Classification
by Mostafa Erfani, Iman Keivanloo and Juergen Rilling

Clustering Support for Fault Prediction in Software
by Maria La Becca - SLIDES

Using Software Vocabulary to Rank Classes that are Probably Impacted by a Bug Report
by Diego Cavalcanti, Katyusco Santos, Dalton Serey and Jorge Figueiredo

Linking E-Mails and Source Code through a Probabilistic Information Retrieval Approach
by Giuseppe Scanniello, Raffaele Branda and Anna Tolve - SLIDES

On The Road to Hades--Helpful Automatic Development Email Summarization
by Alberto Bacchelli, Michele Lanza and Ebrisa Savina Mastrodicasa - SLIDES

Automatic Query Quality Assessment for the Retrieval of Software Artifacts
by Sonia Haiduc, Gabriele Bavota, Rocco Oliveto, Andrian Marcus and Andrea De Lucia

An Implicit Feedback-based Approach to the Evaluation of Text Analysis Techniques for Software Engineerin
by Kostadin Damevski, David Shepherd and Lori Pollock - SLIDES

Towards a Prediction Model for Source Code Vocabulary
by Katyusco De Farias Santos, Dalton Dario Serey Guerrero, Jorge Figueiredo and Roberto A. Bittencourt


SESSION 2 - DISCUSSION from 16:45 to 17:35 pm

0:05 Talk summaries and a discussion of the state of the art
0:25 Small group brain storming on future research in Text Analysis in Software Maintenance - SLIDES
0:10 Discussion of appropriate evaluation metrics - SLIDES | IR book by Manning, Raghavan, and Sch├╝tze
0:10 Presentation of the roadmap



1st Workshop on on The Next Five Years of Text Analysis in Software Maintenance