hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.24138/jcomss.v16i4.935

A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation

Fatima Zohra Ennaji ; Cadi Ayyad University, Marrakech, Morocco
Abdelaziz El Fazziki ; Cadi Ayyad University, Marrakech, Morocco
Hasna El Alaoui El Abdallaoui ; Cadi Ayyad University, Marrakech, Morocco
Hamada El Kabtane ; Cadi Ayyad University, Marrakech, Morocco

Puni tekst: engleski, pdf (2 MB) str. 285-295 preuzimanja: 94* citiraj
APA 6th Edition
Zohra Ennaji, F., El Fazziki, A., El Abdallaoui, H.E.A. i El Kabtane, H. (2020). A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation. Journal of Communications Software and Systems, 16 (4), 285-295. https://doi.org/10.24138/jcomss.v16i4.935
MLA 8th Edition
Zohra Ennaji, Fatima, et al. "A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation." Journal of Communications Software and Systems, vol. 16, br. 4, 2020, str. 285-295. https://doi.org/10.24138/jcomss.v16i4.935. Citirano 25.02.2021.
Chicago 17th Edition
Zohra Ennaji, Fatima, Abdelaziz El Fazziki, Hasna El Alaoui El Abdallaoui i Hamada El Kabtane. "A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation." Journal of Communications Software and Systems 16, br. 4 (2020): 285-295. https://doi.org/10.24138/jcomss.v16i4.935
Harvard
Zohra Ennaji, F., et al. (2020). 'A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation', Journal of Communications Software and Systems, 16(4), str. 285-295. https://doi.org/10.24138/jcomss.v16i4.935
Vancouver
Zohra Ennaji F, El Fazziki A, El Abdallaoui HEA, El Kabtane H. A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation. Journal of Communications Software and Systems [Internet]. 2020 [pristupljeno 25.02.2021.];16(4):285-295. https://doi.org/10.24138/jcomss.v16i4.935
IEEE
F. Zohra Ennaji, A. El Fazziki, H.E.A. El Abdallaoui i H. El Kabtane, "A Crowdsourcing Based Framework for Sentiment Analysis: A Product Reputation", Journal of Communications Software and Systems, vol.16, br. 4, str. 285-295, 2020. [Online]. https://doi.org/10.24138/jcomss.v16i4.935

Sažetak
As social networking has spread, people started sharing their personal opinions and thoughts widely via these online platforms. The resulting vast valuable data represent a rich source for companies to deduct their products’ reputation from both social media and crowds’ judgments. To exploit this wealth of data, a framework was proposed to collect opinions and rating scores respectively from social media and crowdsourcing platform to perform sentiment analysis, provide insights about a product and give consumers’ tendencies. During the analysis process, a consumer category (strict) is excluded from the process of reaching a majority consensus. To overcome this, a fuzzy clustering is used to compute consumers’ credibility. The key novelty of our approach is the new layer of validity check using a crowdsourcing component that ensures that the results obtained from social media are supported by opinions extracted directly from real-life consumers. Finally, experiments are carried out to validate this model (Twitter and Facebook were used as data sources). The obtained results show that this approach is more efficient and accurate than existing solutions thanks to our two-layer validity check design.

Ključne riječi
Crowdsourcing, Product Reputation, Sentiment analysis, Social Media, Subjectivity Classification

Hrčak ID: 246585

URI
https://hrcak.srce.hr/246585

Posjeta: 177 *