T1 - T2

[amritbhanu]

T1 - T2

[amritbhanu]

@timm Prof. any comments? I am looking for min 5 terms to be matched to be considered for a topic overlap.

[timm]

are these results stable? i.e. different runs generate different topics?

and is there any discussion in the literature about lda topic instability?

[amritbhanu]

• These are the graphs talking about stability. With min x terms matched, the same topic is being generated in x% of times. Some topics (~20%) are generated in all the runs.
• But there has been like next to none overlap between T1 and T2.
• Will get back to you on the literature review. There has been some studies.

Project A - T1

Project A - T2

[timm]

cant get an executive summary of these.

only 20% of these topics are stable across multiple runs?

if run N times and collect the topics in all N are there repeated patterns?

[amritbhanu]

stable means: if a topic has occurred more than 5 times in 10 runs. This answers your 3rd question as well.
And yes only 20% of topics are stable. But here I am only finding top 10 topics.

[timm]

Hmmm.... looks liek its time to check if anyone else has found topics to be unstable

is this apper useful to you?

How to Effectively Use Topic Models for Software Engineering Tasks? An Approach Based on Genetic Algorithms ==> paper

@inproceedings{panichella2013effectively,
title={How to effectively use topic models for software engineering tasks? an approach based on genetic algorithms},
author={Panichella, Annibale and Dit, Bogdan and Oliveto, Rocco and Di Penta, Massimiliano and Poshyvanyk, Denys and De Lucia, Andrea},
booktitle={Proceedings of the 2013 International Conference on Software Engineering},
pages={522--531},
year={2013},
organization={IEEE Press}
}

using "grid-serach" idea to tune 4 hyper-parameters of LDA, each divided into 10 bins, to investigate "What is the impact of the configuration parameters on LDA’s performance in the context of software engineering tasks"

This research question aims at justifying the need for an automatic approach that calibrates LDA’s
settings when LDA is applied to support SE tasks. they analyzed a large number of LDA configurations
for three software engineering tasks. The presence of a high variability in LDA’s performances indicates that, without a proper calibration, such a technique risks being severely under-utilized

[timm]

do you know how to find who has cited a paper?

Step1: look for it in google scholar

https://scholar.google.com/scholar?hl=en&q=How+to+effectively+use+topic+models+for+software+engineering+tasks%3F+an+approach+based+on+genetic+algorithms&btnG=&as_sdt=1%2C34&as_sdtp=

Step3: click on the "cited by 73" link :

https://scholar.google.com/scholar?cites=9122112158639969994&as_sdt=5,34&sciodt=0,34&hl=en

enjoy!