%0 Generic %1 kou2023automated %A Kou, Bonan %A Chen, Muhao %A Zhang, Tianyi %D 2023 %K javascript %T Automated Summarization of Stack Overflow Posts %U http://arxiv.org/abs/2305.16680 %X Software developers often resort to Stack Overflow (SO) to fill their programming needs. Given the abundance of relevant posts, navigating them and comparing different solutions is tedious and time-consuming. Recent work has proposed to automatically summarize SO posts to concise text to facilitate the navigation of SO posts. However, these techniques rely only on information retrieval methods or heuristics for text summarization, which is insufficient to handle the ambiguity and sophistication of natural language. This paper presents a deep learning based framework called ASSORT for SO post summarization. ASSORT includes two complementary learning methods, ASSORT_S and ASSORT_IS, to address the lack of labeled training data for SO post summarization. ASSORT_S is designed to directly train a novel ensemble learning model with BERT embeddings and domainspecific features to account for the unique characteristics of SO posts. By contrast, ASSORT_IS is designed to reuse pre-trained models while addressing the domain shift challenge when no training data is present (i.e., zero-shot learning). Both ASSORT_S and ASSORT_IS outperform six existing techniques by at least 13% and 7% respectively in terms of the F1 score. Furthermore, a human study shows that participants significantly preferred summaries generated by ASSORT_S and ASSORT_IS over the best baseline, while the preference difference between ASSORT_S and ASSORT_IS was small.

@misc{kou2023automated, abstract = {Software developers often resort to Stack Overflow (SO) to fill their programming needs. Given the abundance of relevant posts, navigating them and comparing different solutions is tedious and time-consuming. Recent work has proposed to automatically summarize SO posts to concise text to facilitate the navigation of SO posts. However, these techniques rely only on information retrieval methods or heuristics for text summarization, which is insufficient to handle the ambiguity and sophistication of natural language. This paper presents a deep learning based framework called ASSORT for SO post summarization. ASSORT includes two complementary learning methods, ASSORT_S and ASSORT_{IS}, to address the lack of labeled training data for SO post summarization. ASSORT_S is designed to directly train a novel ensemble learning model with BERT embeddings and domainspecific features to account for the unique characteristics of SO posts. By contrast, ASSORT_{IS} is designed to reuse pre-trained models while addressing the domain shift challenge when no training data is present (i.e., zero-shot learning). Both ASSORT_S and ASSORT_{IS} outperform six existing techniques by at least 13% and 7% respectively in terms of the F1 score. Furthermore, a human study shows that participants significantly preferred summaries generated by ASSORT_S and ASSORT_{IS} over the best baseline, while the preference difference between ASSORT_S and ASSORT_{IS} was small.}, added-at = {2023-07-11T04:02:52.000+0200}, author = {Kou, Bonan and Chen, Muhao and Zhang, Tianyi}, biburl = {https://www.bibsonomy.org/bibtex/2169cbd6c1b27b97b7c3721b785d97420/woobanseok}, description = {Automated Summarization of Stack Overflow Posts}, interhash = {e1fe7ec4b2a5869e29d4bf9ee58934fb}, intrahash = {169cbd6c1b27b97b7c3721b785d97420}, keywords = {javascript}, note = {cite arxiv:2305.16680Comment: ICSE 2023}, timestamp = {2023-07-11T04:02:52.000+0200}, title = {Automated Summarization of Stack Overflow Posts}, url = {http://arxiv.org/abs/2305.16680}, year = 2023 }