Social media mining at OpenKnowledge
10 giugno 2014
Social media mining at OpenKnowledge
At OpenKnowledge, we are often asked to improve management and business decisions enhancing customer journeys and experiences, relationship and content marketing practices, digital and social media strategies. In our projects, we suggest to improve the “listening” readiness of the company mining a staggering amount of social data, accessible today as never before – from social conversations to social images. To enhance social business intelligence for clients benefits, we usually use a wide range of socio-analytical tools and methodologies. In fact, in our innovation attitude, we continuously scout and scan for platforms, techniques. As a recent book outlines “researchers should—and must—constantly scan the landscape of technological and social change to look for new methods and tools to employ” (“Social Media, Sociality and Survey Research”). In a recent case where Openknowledge was involved, the board of a large international company was pressing for gathering marketing and business insights to build a fitting social media strategy. To support the client’s business needs, OpenKnowledge envisioned and implemented a sophisticated social media mining project mixing innovative platforms and methods in order to gather marketing and business insights. The first pillar of the social mining project was the social conversations monitoring. Using a listening platform and a range of selected keywords, we collected a large amount of social customer conversations measuring the volume and the sentiment of the mentions of the brands and the products. A second pillar (using a more qualitative nethnographic approach) was to map the topics and themes positioning a qualitative quadrant (x,y) to identify the semantic universe related to the topics. The third pillar focused on a twitter network analysis for communities detections: using specific hashtag, we visualized communities and clusters of customers, prospects and influencers. In addition, we used sub-hashtag (secondary hashtag often cited together with the main hashtag) to find niche communities and diversified clusters closed to the main group. The twitter graphs extract many significant information for the client about the nature and the dynamics of social networks in microblogging environments. The forth pillar, a potential new insight direction for our project, is to mine also the social photo data of the brand consumers to analyze the behaviors and the attitudes or the real contexts of usage of the products. The results of this complex social media mining project were used, also, for different social business objectives: a) to feed a renewed content strategy with relevant topics for participants; b) to identify influencers and advocates for viral communication and marketing strategy; c) to scout consumer-driven product innovations; d) to check the consumer sentiment toward the brands, products and competitors. As a recent book on social media mining correctly outlines: “We can now integrate social theories with computational methods to study how individuals (also known as social atoms) interact and how communities (i.e., social molecules) form. The uniqueness of social media data calls for novel data mining techniques that can effectively handle user generated content with rich social relations. The study and development of these new techniques are under the purview of social media mining, an emerging discipline under the umbrella of data mining. Social Media Mining is the process of representing, analyzing, and extracting actionable patterns from social media data. Social Media Mining, introduces basic concepts and principal algorithms suitable for investigating massive social media data; it discusses theories and methodologies from different disciplines such as computer science, data mining, machine learning, social network analysis, network science, sociology, ethnography, statistics, optimization, and mathematics. It encompasses the tools to formally represent, measure, model, and mine meaningful patterns from large-scale social media data. Social media mining cultivates a new kind of data scientist who is well versed in social and computational theories, specialized to analyze recalcitrant social media data, and skilled to help bridge the gap from what we know (social and computational theories) to what we want to know about the vast social media world with computational tools” (“Social Media Mining. An Introduction”).
Books References and Links:
“Social Media, Sociality and Survey Research”, edited by Craig A. Hill, Elizabeth Dean, Joe Murphy; Wiley, 2014
“Social Media Mining. An Introduction”, Reza Zafarani, Mohammad Ali Abbasi, Huan Liu; Cambridge University Press, 2014