An Approach of Extracting Feature Requests from App Reviews

Peng, Zhenlian; Jian, Wang; He, Ke; Tang, Mingdong

doi:10.1007/978-3-319-59288-6_28

Cited by 7 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering is thus widely used as an exploratory analysis technique to infer topics commonly discussed by users (Pagano and Maalej 2013;Guzman and Maalej 2014;Liu et al 2018) and aggregate reviews containing semantically related information (Chen et al 2014;Palomba et al 2017;Zhou et al 2020). Clustering can be used for grouping reviews that request the same feature (Peng et al 2016;Di Sorbo et al 2016), report similar problems (Martin et al 2015;Villarroel et al 2016;Gao et al 2018b;Williams et al 2020), or discuss a similar characteristic of the app (Vu et al 2016;Chen et al 2019;Xiao et al 2020). The generated clusters might help software engineers synthesize information from a group of reviews referring to the same topics rather than examining each review individually (Fu et al 2013;Hadi and Fard 2020).…”

Section: Clusteringmentioning

confidence: 99%

“…Pattern matching techniques (employed in 22 studies) localize parts of review text (or its linguistic analysis) matching hand-crafted patterns. Such patterns can take many forms, such as, regular expressions (Yang and Liang 2015;Groen et al 2017;Uddin et al 2020), PoS sequences (Vu et al 2016;Johann et al 2017), dependencies between words (Gu and Kim 2015;Peng et al 2016;Di Sorbo et al 2017;Srisopha et al 2020c) or simple keyword matching (Yang and Liang 2015;Di Sorbo et al 2017;Tao et al 2020). The technique has been adopted in Information Extraction e.g., to extract requirements from reviews (Yang and Liang 2015;Groen et al 2017), Classification e.g., to classify requirements into functional and non-functional (Yang and Liang 2015) and Summarization e.g., to provide a bug report summary (Groen et al 2017).…”

Section: Natural Language Processingmentioning

confidence: 99%

“…User Request Type Precision range from 35% to 94% (Martin et al 2015;Jha and Mahmoud 2017b) with the median precision of 80% (Song et al 2020); recall range from 51% to 99% (Jha and Mahmoud 2017b;Puspaningrum et al 2018) with the median recall of 82% (Peng et al 2016;Oh et al 2013).…”

Section: Classificationmentioning

confidence: 99%

“…Classification App reviews can be classified by information types these reviews contain, such as user requests, NFRs and issues. State-of-the-art review classification techniques have a median precision above 81% (Yang and Liang 2015;Lu and Liang 2017;Deshpande and Rokne 2018;Scoccia et al 2018) and median recall around 83% (Peng et al 2016;Lu and Liang 2017;Scoccia et al 2018;Nayebi et al 2018;Jha and Mahmoud 2019).…”

Section: Information Extractionmentioning

confidence: 99%

“…,Shah et al (2016),Iacob et al (2016), Di,Peng et al (2016),,Villarroel et al (2016), Di,Johann et al (2017),Abad et al (2017),Groen et al (2017),Zhang et al (2017),Deocadez et al (2017b),Lu and Liang (2017),Williams and Mahmoud (2018),Dhinakaran et al (2018),Ciurumelea et al (2018),Li et al (2018),, AlSubaihin et al (2019), Liu et al (2019), Chen et al (2019), Jha and Mahmoud (2019), Da ¸browski et al (2019), Dalpiaz and Parente (2019), Al Kilani et al (2019), Scalabrino et al (2019), Shah et al (2019c), Da ¸browski et al (2020), Srisopha et al (2020b), Song et al (2020), Uddin et al (2020), Wen and Chen (2020), Gao et al (2020), Tizard et al (2020), van Vliet et al (2020), Guo and Singh (2020), Li et al (2020), Hadi and Fard (2020), Wang et al (2020b), Kunaefi and Aritsugi (2020), Xiao et al (2020), Liu et al (2020), and Sharma and Bashir (2020) Requirements Classification 10 5% Yang and Liang (2015), Deocadez et al (2017a), Groen et al (2017), Lu and Liang (2017), Wang et al (2018), Wang et al (2018), Jha and Mahmoud (2019), Wen and Chen (2020), van Vliet et al (2020), and Wang et al (2020b) Requirements Prioritization 19 10% Hoon et al (2012), Vasa et al (2012), Pagano and Maalej (2013), Guzman and Maalej (2014), Guzman et al (2015), Maalej et al (2016), Villarroel et al (2016), Johann et al (2017), Kurtanović and Maalej (2017), Groen et al (2017), Kurtanovic and Maalej (2018), Scalabrino et al (2019), Shah et al (2019c), Zhang et al (2019), AlSubaihin et al (2019), Da ¸browski et al (2020), Srisopha et al (2020b), Oehri and Guzman (2020), and Di Sorbo et al (2020) Requirements Specification 6 3% Pagano and Maalej (2013), Maalej et al (2016), Maalej et al (2016), Kurtanović and Maalej (2017), Kurtanovic and Maalej (2018), and Williams et al . (2013), Iacob and Harrison (2013), Iacob et al (2013a), Iacob et al (2013b), Guzman et al (2014), Guzman and Maalej (2014), Maalej and Nabil (2015), Gu and Kim (2015), Man et al (2016), Maalej et al (2016), Bakiu and Guzman (2017), Ciurumelea et al (2018), Liu et al (2018),...…”

mentioning

confidence: 99%

See 4 more Smart Citations

Analysing app reviews for software engineering: a systematic literature review

et al. 2022

View full text Add to dashboard Cite

App reviews found in app stores can provide critically valuable information to help software engineers understand user requirements and to design, debug, and evolve software products. Over the last ten years, a vast amount of research has been produced to study what useful information might be found in app reviews, and how to mine and organise such information as efficiently as possible. This paper presents a comprehensive survey of this research, covering 182 papers published between 2012 and 2020. This survey classifies app review analysis not only in terms of mined information and applied data mining techniques but also, and most importantly, in terms of supported software engineering activities. The survey also reports on the quality and results of empirical evaluation of existing techniques and identifies important avenues for further research. This survey can be of interest to researchers and commercial organisations developing app review analysis techniques and to software engineers considering to use app review analysis.

show abstract

Section: Clusteringmentioning

confidence: 99%

Section: Natural Language Processingmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Section: Information Extractionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Analysing app reviews for software engineering: a systematic literature review

et al. 2022

View full text Add to dashboard Cite

show abstract

The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review

2022

View full text Add to dashboard Cite

Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-toprocess representations, such as lists of features or embedding-based vector representations. These NLPbased representations are usually used at a later stage as inputs for machine learning techniques or rulebased methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out (1) what are the representations used in RE tasks literature, (2) what is the main focus of these works, (3) what are the main research directions in this domain, and ( 4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.

show abstract