Exploring programming semantic analytics with deep learning models

Yihan Lu, Ihan Hsiao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There are numerous studies have reported the effectiveness of example-based programming learning. However, less is explored recommending code examples with advanced Machine Learning-based models. In this work, we propose a new method to explore the semantic analytics between programming codes and the annotations. We hypothesize that these semantics analytics will capture mass amount of valuable information that can be used as features to build predictive models. We evaluated the proposed semantic analytics extraction method with multiple deep learning algorithms. Results showed that deep learning models outperformed other models and baseline in most cases. Further analysis indicated that in special cases, the proposed method outperformed deep learning models by restricting false-positive classifications.

Original languageEnglish (US)
Title of host publicationProceedings of the 9th International Conference on Learning Analytics and Knowledge
Subtitle of host publicationLearning Analytics to Promote Inclusion and Success, LAK 2019
PublisherAssociation for Computing Machinery
Pages155-159
Number of pages5
ISBN (Electronic)9781450362566
DOIs
StatePublished - Mar 4 2019
Event9th International Conference on Learning Analytics and Knowledge, LAK 2019 - Tempe, United States
Duration: Mar 4 2019Mar 8 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference9th International Conference on Learning Analytics and Knowledge, LAK 2019
CountryUnited States
CityTempe
Period3/4/193/8/19

Fingerprint

Computer programming
Semantics
Learning algorithms
Learning systems
Deep learning

Keywords

  • Coding concept detection
  • Deep learning
  • Programming semantics
  • Semantic modeling
  • Text based classification

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Lu, Y., & Hsiao, I. (2019). Exploring programming semantic analytics with deep learning models. In Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019 (pp. 155-159). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3303772.3303823

Exploring programming semantic analytics with deep learning models. / Lu, Yihan; Hsiao, Ihan.

Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. Association for Computing Machinery, 2019. p. 155-159 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lu, Y & Hsiao, I 2019, Exploring programming semantic analytics with deep learning models. in Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 155-159, 9th International Conference on Learning Analytics and Knowledge, LAK 2019, Tempe, United States, 3/4/19. https://doi.org/10.1145/3303772.3303823
Lu Y, Hsiao I. Exploring programming semantic analytics with deep learning models. In Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. Association for Computing Machinery. 2019. p. 155-159. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3303772.3303823
Lu, Yihan ; Hsiao, Ihan. / Exploring programming semantic analytics with deep learning models. Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. Association for Computing Machinery, 2019. pp. 155-159 (ACM International Conference Proceeding Series).
@inproceedings{9d5c4b7cd34545bbbd47fb7b7b1ba57a,
title = "Exploring programming semantic analytics with deep learning models",
abstract = "There are numerous studies have reported the effectiveness of example-based programming learning. However, less is explored recommending code examples with advanced Machine Learning-based models. In this work, we propose a new method to explore the semantic analytics between programming codes and the annotations. We hypothesize that these semantics analytics will capture mass amount of valuable information that can be used as features to build predictive models. We evaluated the proposed semantic analytics extraction method with multiple deep learning algorithms. Results showed that deep learning models outperformed other models and baseline in most cases. Further analysis indicated that in special cases, the proposed method outperformed deep learning models by restricting false-positive classifications.",
keywords = "Coding concept detection, Deep learning, Programming semantics, Semantic modeling, Text based classification",
author = "Yihan Lu and Ihan Hsiao",
year = "2019",
month = "3",
day = "4",
doi = "10.1145/3303772.3303823",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "155--159",
booktitle = "Proceedings of the 9th International Conference on Learning Analytics and Knowledge",

}

TY - GEN

T1 - Exploring programming semantic analytics with deep learning models

AU - Lu, Yihan

AU - Hsiao, Ihan

PY - 2019/3/4

Y1 - 2019/3/4

N2 - There are numerous studies have reported the effectiveness of example-based programming learning. However, less is explored recommending code examples with advanced Machine Learning-based models. In this work, we propose a new method to explore the semantic analytics between programming codes and the annotations. We hypothesize that these semantics analytics will capture mass amount of valuable information that can be used as features to build predictive models. We evaluated the proposed semantic analytics extraction method with multiple deep learning algorithms. Results showed that deep learning models outperformed other models and baseline in most cases. Further analysis indicated that in special cases, the proposed method outperformed deep learning models by restricting false-positive classifications.

AB - There are numerous studies have reported the effectiveness of example-based programming learning. However, less is explored recommending code examples with advanced Machine Learning-based models. In this work, we propose a new method to explore the semantic analytics between programming codes and the annotations. We hypothesize that these semantics analytics will capture mass amount of valuable information that can be used as features to build predictive models. We evaluated the proposed semantic analytics extraction method with multiple deep learning algorithms. Results showed that deep learning models outperformed other models and baseline in most cases. Further analysis indicated that in special cases, the proposed method outperformed deep learning models by restricting false-positive classifications.

KW - Coding concept detection

KW - Deep learning

KW - Programming semantics

KW - Semantic modeling

KW - Text based classification

UR - http://www.scopus.com/inward/record.url?scp=85062772525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062772525&partnerID=8YFLogxK

U2 - 10.1145/3303772.3303823

DO - 10.1145/3303772.3303823

M3 - Conference contribution

AN - SCOPUS:85062772525

T3 - ACM International Conference Proceeding Series

SP - 155

EP - 159

BT - Proceedings of the 9th International Conference on Learning Analytics and Knowledge

PB - Association for Computing Machinery

ER -