Weighted aspect-based opinion mining using deep learning for recommender system

Da’u, Aminu; Salim, Naomie; Rabiu, Idris; Osman, Akram

doi:10.1016/j.eswa.2019.112871

Cited by 65 publications

(28 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have attempted to compute opinion polarity based on aggregating the individual scores of the different aspects that compose the opinion [35][36][37][38]; nonetheless, other approaches present alternative mechanisms, based on the idea that the polarity must be calculated in terms of other variables working together rather than individual calculating the scores/variables as if each was working separately [39].…”

Section: Affective Computing and Sentiment Analysismentioning

confidence: 99%

“…Furthermore, the vast majority are based on the use of fuzzy logic techniques [40][41][42]. The latter studies, on the other hand, tend to be based on statistical models such as latent Dirichlet allocation (LDA) [43], deep learning [39,44], stochastic theory [45] or even graph-based approaches [46], among others.…”

Section: Affective Computing and Sentiment Analysismentioning

confidence: 99%

See 1 more Smart Citation

Ordered Weighted Averaging for Emotion-Driven Polarity Detection

2021

View full text Add to dashboard Cite

The overall rating of an opinion can generally be considered as the aggregation of the individual ratings of all features of that opinion. Nevertheless, there are cases in which the overall rating differs substantially from the mean or weighted mean of the ratings of the individual features. These cases can be explained in terms of user mood. To address this problem, this study introduces a fuzzy framework for computing user mood based on SenticNet and sentic patterns, which are used to guide an ordered weighted averaging operator. This operator allows the aggregation to be computed in such a way as to provide an understanding of why some positive or negative aspects are considered to a greater or lesser extent. The performance and advantages of this proposal are illustrated in depth via a variety of scenarios applied to real data. The results show a promising framework applicable to other tools, such as customized recommender systems or decision support systems.

show abstract

Section: Affective Computing and Sentiment Analysismentioning

confidence: 99%

Section: Affective Computing and Sentiment Analysismentioning

confidence: 99%

Ordered Weighted Averaging for Emotion-Driven Polarity Detection

2021

View full text Add to dashboard Cite

show abstract

“…A recommendation model based on a weighted feature-based sentiment analysis using a deep learning approach is proposed in [16]. The model had two main components: the feature-based sentiment analysis component and the recommendation generation component.…”

Section: Related Workmentioning

confidence: 99%

Ontology-Based Approach for Feature Level Sentiment Analysis

Aboelela

Gad

Ismail

2021

IJICIS

View full text Add to dashboard Cite

Through the state-of-the-art digitalization, we can see a massive growth in user-generated content on the web that provides feedback from people on a variety of topics. However, manually managing large-scale user feedback would be a difficult task and a waste of time. Therefore, the concept of sentiment analysis is emerged. Sentiment analysis is a computerized study of individuals' feelings and opinions about an entity or product. It can be executed at three different levels: document level, sentence or phrase level, and feature level. This paper proposes a novel ontologybased approach for feature level sentiment analysis. The proposed approach extracts the product features using semantic similarity and Wordnet ontology and uses the SentiWordent dictionary to classify the users' comments as positive and negative. Furthermore, it manages negative words to obtain more precise classification results. The proposed approach is assessed by using two benchmark amazon products' datasets in terms of accuracy; recall, precision, and f-measure. The performance reaches to 92.4% accuracy, 97.2% precision, 92.8 % recall, and 94.4% f-measure.

show abstract

“…These categories of approaches have been applied in many research. For example the work of [28][29][30][31] represent techniques that utilized the supervised approach. While the work of [32][33][34][35] applied the semi-supervised approach in the ABSA .…”

Section: Related Workmentioning

confidence: 99%