Replication issues in syntax-based aspect extraction for opinion mining

Marrese-Taylor, Edison; Matsuo, Yutaka

doi:10.18653/v1/e17-4003

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A trained classifier for the target domain, clustering was utilized as it reduced the gap between domain-specific words of various domains. Marrese-Taylor et al [8] introduced a replicability issues in syntactic centric aspect-based opinion mining. It focused syntactic techniques, which tend to demonstrate a lower level of transparency due to the increasing level of model complexity and the lack of code accessibility.…”

Section: Introductionmentioning

confidence: 99%

To Improve Feature Extraction and Opinion Classification Issues in Customer Product Reviews Utilizing an Efficient Feature Extraction and Classification (EFEC) Algorithm

Solainayagi¹,

Ponnusamy²

2018

IJEECS

View full text Add to dashboard Cite

<span lang="EN-US">Currently, customer's product review opinion plays an essential role in deciding the purchasing of the online product. A customer prefers to acquire the opinion of other customers by viewing their opinion during online products' reviews, blogs and social networking sites, etc. The majority of the product reviews including huge words. A few users provide the opinion; it is tough to analysis and understands the meaning of reviews. To improve user fulfillment and shopping experience, it has become a general practice for online sellers to allow their users to review or to communicate opinions of the products that they have sold. The major goal of the paper is to solve feature extraction problem and opinion classification problem from customers utilized product reviews which extract the feature words and opinion words from product reviews. To propose an Efficient Feature Extraction and Classification (EFEC) algorithm is implementing to extracts a feature from opinion words. The reviewer usually marks both positive and negative parts of the reviewed product, despite the fact that their general opinion on the product may be positive or negative. An EFEC algorithm is utilized to predict the number of positive and negative opinion in reviews. Based on Experimental evaluations, proposed algorithm improves accuracy 15.05%, precision 13.7%, recall 15.59% and F-measure 15.07% of the proposed system compared than existing methodologies</span>

show abstract

Section: Introductionmentioning

confidence: 99%

To Improve Feature Extraction and Opinion Classification Issues in Customer Product Reviews Utilizing an Efficient Feature Extraction and Classification (EFEC) Algorithm

Solainayagi¹,

Ponnusamy²

2018

IJEECS

View full text Add to dashboard Cite

show abstract

Replication of Studies in Empirical Software Engineering: A Systematic Mapping Study, From 2013 to 2018

et al. 2020

View full text Add to dashboard Cite

In any discipline, replications of empirical studies are necessary to consolidate the acquired knowledge. In Software Engineering, replications have been reported since the 1990s, although their number is still small. The difficulty in publishing, the lack of guidelines, and the unavailability of replication packages are pointed out by the community as some of the main causes. Objective: Understanding the current state of replications in Software Engineering studies by evaluating current trends and evolution during the last 6 years. Method: A Systematic Mapping Study including articles published in the 2013-2018 period that report at least one replication of an empirical study in Software Engineering. Results: 137 studies were selected and analysed, identifying: i) forums; ii) authors, co-authorships and institutions; iii) most cited studies; iv) research topics addressed; v) empirical methods used; vi) temporal distribution of publications; and vii) distribution of studies according to research topics and empirical methods. Conclusions: According to our results, the most relevant forums are the Empirical Software Engineering and Information and Software Technology journals, and the Empirical Software Engineering and Measurement conference. We observed that, as in previous reviews by other researchers, most of the studies were carried out by European institutions, especially Italian, Spanish, and German researchers and institutions. The studies attracting more citations were published mainly in journals and in the International Conference on Software Engineering. Testing, requirements, and software construction were the most frequent topics of replication studies, whereas the usual empirical method was the controlled experiment. On the other hand, we identified research gaps in areas such as software engineering process, software configuration management, and software engineering economics. When analysed together with previous reviews, there is a clear increasing trend in the number of published replications in the 2013-2018 period. INDEX TERMS Empirical software engineering, replications, systematic mapping study.

show abstract

NLP Community Perspectives on Replicability

Mieskes¹,

Fort

Névéol

et al. 2019

Proceedings - Natural Language Processing in a Deep Learning World

View full text Add to dashboard Cite

With recent efforts in drawing attention to the task of replicating and/or reproducing 1 results, for example in the context of COLING 2018 and various LREC workshops, the question arises how the NLP community views the topic of replicability in general. Using a survey, in which we involve members of the NLP community, we investigate how our community perceives this topic, its relevance and options for improvement. Based on over two hundred participants, the survey results confirm earlier observations, that successful reproducibility requires more than having access to code and data. Additionally, the results show that the topic has to be tackled from the authors', reviewers' and community's side.

show abstract

Replication issues in syntax-based aspect extraction for opinion mining

Cited by 4 publications

References 27 publications

To Improve Feature Extraction and Opinion Classification Issues in Customer Product Reviews Utilizing an Efficient Feature Extraction and Classification (EFEC) Algorithm

To Improve Feature Extraction and Opinion Classification Issues in Customer Product Reviews Utilizing an Efficient Feature Extraction and Classification (EFEC) Algorithm

Replication of Studies in Empirical Software Engineering: A Systematic Mapping Study, From 2013 to 2018

NLP Community Perspectives on Replicability

Contact Info

Product

Resources

About