TY  - CONF
T1  - Mining and Visualizing Social Data to Inform Marketing Decisions
A1  - Treboux, Jerome
A1  - Cretton, Fabian
A1  - Evéquoz, Florian
A1  - Calvé, Anne Le
A1  - Genoud, Dominique
TI  - Proceedings of the 2016 IEEE 30th International Conference on Advanced Information Networking and Applications
Y1  - 2016
SP  - 66
EP  - 73
T2  - IEEE
CY  - Crans-Montana, Switzerland
SN  - 1550-445X
M2  - doi: 10.1109/AINA.2016.130
KW  - d3
KW  - data mining
KW  - data visualization
KW  - KNIME
KW  - Linked Data
KW  - marketing
KW  - Methodology
KW  - social media
N2  - Most of today’s commercial companies heavily rely on social media and community management tools to interact with their clients and analyze their online behaviour. Nonetheless, these tools still lack evolved data mining and visualization features to tailor the analysis in order to support useful marketing decisions.We present an original methodology that aims at formalizing the marketing need of the company and develop a tool that can support it. The methodology is derived from the Cross-Industry Standard Process for Data Mining (CRISP-DM) and includes additional steps dedicated to the design and development of visualizations of mined data. We followed the methodology in two use cases with Swiss companies. First, we developed a prototype that aims at understanding the needs of tourists based on Flickr and Instagram data. In that use case, we extend the existing literature by 
enriching hashtags analysis methods with a semantic network based on Linked Data. Second, we analyzed internal customer data of an online discount retailer to help them define guerilla marketing measures. We report on the challenges of integrating Facebook data in the process. Informal feedback from domain experts confirms the strong potential of such advanced analytic features based on social data to inform marketing decisions.
ER  -