Abstract: Data characterizing a document including a target word and a plurality of potential meanings for the target word is received. A first set of context words is determined using a language model. The first set of context words is for the target word. A second set of context words is determined using a knowledge base and the language model. The second set of context words is for the plurality of potential meanings of the target word. A score is determined for each of the plurality of potential meanings by at least comparing the first set of context words and the second set of context words. A potential meaning selected from the plurality of potential meanings that has a highest score is selected as a disambiguation of the first word. Related apparatus, systems, techniques and articles are also described.

Abstract: Data characterizing a result set corresponding to a query of a social media dataset can be received. The query can include a first context including a first context identifier. The result set can include a first entity and a second entity. The first entity can include a first entity identifier and the second entity can include a second entity identifier. A key set can include a first fixed length key characterizing the first entity identifier in the first context. The key set can further include a second fixed length key characterizing the second entity identifier in the first context. The key set including the first fixed length key and the second fixed length key can be deduplicated. A first relevance score associated with the first context can be determined using the deduplicated key set. The first relevance score can be provided.

Abstract: Data characterizing a query of a social media dataset can be received. The query can be executed utilizing a distributed processing cluster. The distributed processing cluster can include a plurality of nodes. At least one node can execute a first query on a partition of a tablespace storing a portion of the social media dataset. The partition can include a data source that can include a fixed width unique identifier and a stored field. The fixed width unique identifier can be associated with a respective record of the social media dataset and the stored field can include a portion of the respective record. A result of the query can be provided. Related apparatus, systems, techniques and articles are also described.

Abstract: Data is received characterizing a network represented by a directed graph having nodes and edges. The network includes an influence score associated with a node. The network is associated with a search keyword. A portion of the directed graph and influence score is displayed in a graphical user interface display space. The portion of directed graph is dynamically updated in response to receiving updated network data. Related apparatus, systems, techniques and articles are also described.