Predicting user behavior in electronic markets based on personality-mining in large online social networks

Abstract

Determining a user's preferences is an important condition for effectively operating automatic recommendation systems. Since personality theory claims that a user's personality substantially influences preference, I propose a personality-based product recommender (PBPR) framework to analyze social media data in order to predict a user's personality and to subsequently derive its personalitybased product preferences. The PBRS framework will be evaluated as an IT-artefact with a unique online social network XING dataset and a unique coffeemaker preference dataset. My evaluation results show (a) the possibility of predicting a user's personality from social media data, as I reached a predictive gain between 23.2 and 41.8 percent and (b) the possibility of recommending products based on a user's personality, as I reached a predictive gain of 45.1 percent.

Big Data Analytics Capabilities and Innovation: The Mediating Role of Dynamic Capabilities and Moderating Effect of the Environment

“…The role of BDACs in enhancing incremental innovation capabilities can be discerned in several examples, such as alterations to products and services (Y. Wang, Kung and Byrd, 2018), personalization of offered marketing approaches and services (Buettner, 2017;Xu, Frankwick and Ramirez, 2016), changes in client interfaces (Lehrer et al, 2018), improved efficiency in supply chain management methods (Waller and Fawcett, 2013), as well as modified means of system risk analysis and fault detection (Hu et al, 2010). Similarly, several examples of enhanced radical innovation capabilities are described in the literature, including the development of novel products, such as that of personalized medicine, that integrate systems biology such as genomics with electronic health record data to provide more effective treatments (Alyass, Turcotte and Meyre, 2015), new services such as adaptive learning systems that build on a broad range of data and interactions of users with their learning environments (Maseleno et al, 2018), and developing new processes such as that of decision-aiding tools for detection, characterization and monitoring of diseases in imagerecognition tasks related to radiology, for instance (Hosny et al, 2018).…”

Development of a Machine Learning Based Algorithm To Accurately Detect Schizophrenia based on One-minute EEG Recordings

“…That is why more extensive experimentation is necessary using datasets that contain similar data to schizophrenia behavior. Furthermore, it is sufficiently apparent that medication and personality [50][51][52] influence the EEG data of schizophrenic patients, and as a result, our classifier. While the internal validity of our model is very high due to the rigorous k-fold-crossvalidation, improving external validity by training with additional datasets is also an important step to improve the model.…”

High-performance Diagnosis of Sleep Disorders: A Novel, Accurate and Fast Machine Learning Approach Using Electroencephalographic Data

“…In addition, medication and personality [43][44][45] influence EEG data, and as a result, our classifier. While the internal validity of our model is very high due to the rigorous k-fold-cross-validation, improving external validity by training with additional datasets is also an important step to improve the model.…”