All Publications

ARSeek: Identifying API Resource Using Code and Discussion on Stack Overflow

ARSeek identifies API resources by jointly analyzing code snippets and natural-language discussions on Stack Overflow, outperforming single-modality baselines for developer API queries.

On the Effectiveness of Pretrained Models for API Learning

An empirical study evaluating the effectiveness of pre-trained models for API learning tasks, comparing PTM variants against traditional baselines across API sequence completion and cross-lingual API mapping.

FACOS: Finding API Relevant Contents on Stack Overflow with Semantic and Syntactic Analysis

FACOS combines semantic and syntactic analysis to automatically find API-relevant content on Stack Overflow, outperforming pure keyword-based retrieval for developer API queries.

Evaluating Pre-Trained Models for User Feedback Analysis in Software Engineering

We investigate the benefits of PTMs for app review classification compared to the existing models, as well as the transferability of PTMs in multiple settings.

AOBTM - Adaptive Online Biterm Topic Modeling for Version Sensitive Short-texts Analysis

In this paper, we propose Adaptive Online Biterm Topic Model (AOBTM) to model topics in short texts adaptively. AOBTM alleviates the sparsity problem in short-texts and considers the statistical-data for an optimal number of previous time-slices.

ReviewViz - Assisting Developers Perform Empirical Study on Energy Consumption Related Reviews for Mobile Applications

The developed web-browser based interactive visualization tool is a novel framework that makes it easier for the developers to traverse through the extensive result set generated by the text classification and topic modeling algorithms. It also helps developers to quickly comprehend the outcomes of implemented model feature combinations and algorithms used.

Geo-Spatial Data Visualization and Critical Metrics Predictions for Canadian Elections

The information about Canadian Federal and Provincial Elections exists in numerous websites, as separate tables so that the user needs to traverse through a tree-like structure of scattered information on the site, and the user, at the end, is left with the comparison, on their own, without providing proper data interpretation tools. In this paper, we provide technical details of addressing the problem, by using the Canadian Elections data (since 1867).