Nowadays, several companies use social media marketing to increase profit and control the market. The customer's feedback has a powerful influence on company reputation by conveying their experience in social media. Customers exchange their feedback about the services using electronic Word-of-Mouth (e-WOM). Negative feedback could help companies improve their service to increase profit. In this work, we propose an approach to determine the effect of negative e-WOM relating to a company's products or services. Firstly, we apply a machine-learning algorithm called random forest to classify e-WOM on three classes based on polarity: Positive, negative, or neutral. Secondly, we group negative e-WOM into different clusters based on their topics using a similarity method named cosine similarity. Thirdly, we generate an influence graph of negative e-WOM based on time precedence and social ties. Finally, we analyze the resulted graph to identify risk patterns and convey useful information. The provided method is implemented using Python and is tested with collected data.
الكلمات المفتاحية :
Social media marketing
Electronic word-of-mouth
Social commerce
Machine learning
A. Dembri and M. Gharzouli. 2020. Graph-based Model for Negative e-WOM Influence in Social Media. In Proceedings of the 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech), Marrakeche, Morroco (May 2020), IEEE, 1-6. DOI: https://doi.org/10.1109/CloudTech49835.2020.9365914.
APA :
Dembri, A. & Gharzouli, M. (2020, May). Graph-based Model for Negative e-WOM Influence in Social Media. In Proceedings of the 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech), Marrakeche, Morroco, IEEE, 1-6. DOI: https://doi.org/10.1109/CloudTech49835.2020.9365914
IEEE :
A. Dembri and M. Gharzouli, "Graph-based Model for Negative e-WOM Influence in Social Media". In Proceedings of the 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech), Marrakeche, Morroco, IEEE, pp. 1-6, May, 2020. DOI: https://doi.org/10.1109/CloudTech49835.2020.9365914.
BibTeX :
@inproceedings{misc-lab-349, author = {Dembri, Abderraouf and Gharzouli, Mohamed}, title = {Graph-based Model for Negative e-WOM Influence in Social Media}, booktitle = {5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech)}, location = {Marrakeche, Morroco}, isbn = {978-1-7281-6175-4}, pages = {1--6}, publisher = {IEEE}, year = {2020}, month = {May}, doi = {10.1109/CloudTech49835.2020.9365914}, url = {https://ieeexplore.ieee.org/document/9365914}, keywords = {Social media marketing, Electronic word-of-mouth, Social commerce, Machine learning} }
RIS :
TY - CONF TI - Graph-based Model for Negative e-WOM Influence in Social Media AU - A. Dembri AU - M. Gharzouli PY - 2020 BT - 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech), Marrakeche, Morroco SN - 978-1-7281-6175-4 SP - 1 EP - 6 PB - IEEE AB - Nowadays, several companies use social media marketing to increase profit and control the market. The customer's feedback has a powerful influence on company reputation by conveying their experience in social media. Customers exchange their feedback about the services using electronic Word-of-Mouth (e-WOM). Negative feedback could help companies improve their service to increase profit. In this work, we propose an approach to determine the effect of negative e-WOM relating to a company's products or services. Firstly, we apply a machine-learning algorithm called random forest to classify e-WOM on three classes based on polarity: Positive, negative, or neutral. Secondly, we group negative e-WOM into different clusters based on their topics using a similarity method named cosine similarity. Thirdly, we generate an influence graph of negative e-WOM based on time precedence and social ties. Finally, we analyze the resulted graph to identify risk patterns and convey useful information. The provided method is implemented using Python and is tested with collected data. KW - Social media marketing KW - Electronic word-of-mouth KW - Social commerce KW - Machine learning DO - 10.1109/CloudTech49835.2020.9365914 UR - https://ieeexplore.ieee.org/document/9365914 ID - misc-lab-349 ER -