Abstract: Described is a system for identification of correlations in customer observables (COs). The system extracts key phrases representing COs from textual inputs from multiple data sources, wherein the COs are related to a consumer product. A unified hypergraph is constructed that models co-occurrences of COs. The unified hypergraph includes nodes and types of hyperedges connecting the nodes, where COs are represented by nodes and data sources are represented by different types of hyperedges. Each node of the unified hypergraph is embedded into a latent feature space. The unified hypergraph is partitioned into clusters within the latent feature space, where each cluster contains correlated CO data. The correlated CO data from a cluster are used to generate and provide targeted messages specific to the consumer product to a display device.

Abstract: Described is a system for identification of correlations in customer observables (COs). The system extracts key phrases representing COs from textual inputs from multiple data sources, wherein the COs are related to a consumer product. A unified hypergraph is constructed that models co-occurrences of COs. The unified hypergraph includes nodes and types of hyperedges connecting the nodes, where COs are represented by nodes and data sources are represented by different types of hyperedges. Each node of the unified hypergraph is embedded into a latent feature space. The unified hypergraph is partitioned into clusters within the latent feature space, where each cluster contains correlated CO data. The correlated CO data from a cluster are used to generate and provide targeted messages specific to the consumer product to a display device.

Abstract: Described is a system for identifying emerging trends in a consumer product from heterogeneous online data sources. Data extracted from heterogeneous data sources is fused, and consumer product data is identified from the fused data. A baseline distribution for consumer issues related to consumer products is generated from the set of consumer product data. A deviation value from the baseline distribution is determined for a specific consumer product. Indicators for future consumer issues regarding the specific consumer product are identified based on the deviation value. The indicators are reported to a system analyst.

Abstract: A method for concept word management. The method comprises receiving an editing request for a text document from a requestor. The editing request includes an initial phrase located in the text document. An ontology associated with the text document is searched for the initial phrase. The initial phrase is distinguished in the text document in response to the initial phrase being located in the ontology and to the editing request further including a distinguish phrase command. An alternate phrase associated with the initial phrase is presented to the requestor in response to the initial phrase being located in the ontology and to the editing request further including a display alternate phrase command. The initial phrase is replaced in the text document with the alternate phrase in response to the editing request further including a replace phrase command.