KEYWORD EXTRACTION

1 . A computer-implemented method for keyword extraction, comprising:

extracting a number of keywords from content inside an enterprise social network utilizing pattern recognition;

constructing a semantics graph based on the number of keywords; and

determining content themes within the enterprise social network based on the constructed semantics graph.

2 . The computer-implemented method of claim 1 , wherein determining content themes further comprises finding clusters within the semantics graph in which the number of keywords appear most often.

3 . The computer-implemented method of claim 1 , wherein extracting a number of keywords further comprises:

forming a vector of keywords in a repository of forum threads; and

generating a binary features vector for each thread.

4 . The computer-implemented method of claim 1 , further comprising:

receiving a search request for the enterprise social network, the search request including an input phrase;

determining semantics of the input phrase utilizing the semantics graph; and

retrieving content from within the enterprise social network relevant to the input phrase.

5 . A non-transitory computer-readable medium storing a set of instructions for keyword extraction executable by a processing resource to:

automatically build a repository of keyword tags;

automatically assign a number of keyword tags from within the repository to a number of keywords within content received from an enterprise social network and extract the number of keyword tags;

generate a semantics graph that includes relationships between each of the assigned number of keyword tags; and

cluster sections of the received content into themes based on the semantics graph.

6 . The non-transitory computer-readable medium of claim 5 , wherein the instructions executable to automatically assign a number of keyword tags are further executable to match n-tuples in the content by the tags discovered during keyword tag extraction.

7 . The non-transitory computer-readable medium of claim 5 , wherein the instructions executable to extract the number of keyword tags include instructions executable to filter stop words from the repository and utilize remaining repository words as keywords.

8 . The non-transitory computer-readable medium of claim 5 , wherein the instructions executable to extract the number of keyword tags include instructions executable to compare a word frequency in the repository with a word frequency in a particular language.

9 . The non-transitory computer-readable medium of claim 8 , wherein the instructions executable to extract the number of keyword tags include instructions executable to designate a word as a keyword if the frequency exceeds a frequency threshold in the repository as compared to the particular language.

10 . The non-transitory computer-readable medium of claim 5 , wherein the instructions executable to extract the number of keyword tags include instructions executable to extract the keyword tags utilizing term co-occurrence.

11 . A system, comprising:

a memory resource;

a processing resource coupled to the memory resource to implement:

a corpus builder module configured to retrieve enterprise social network content;

a tag extractor module configured to determine a number of words relevant to a domain of interest, tag the number of words, and automatically extract each of the tags from the retrieved content;

a semantics graph builder module configured to build a semantics graph that includes a relationship between each of the tags; and

a thematization module configured to cluster the semantics graph into themes.

12 . The system of claim 11 , wherein the thematization module is further configured to:

coarsen the semantics graph by iteratively finding a matching semantics graph with matching nodes, and collapsing each set of matched nodes into one node;

partition the coarsened graph by computing an edge-cut bisection of the coarsened graph such that each part of the bisection contains a reduced number of edge weights of the semantics graph; and

project the partitioned graph back to the semantics graph.

13 . The system of claim 11 , wherein the tag extractor module is further configured to identify at least one of a focus word and focus phrase via pattern recognition.

14 . The system of claim 11 , further comprising a computation module configured to compute a minimum number of web links to reach from a seed page to each corpus page on which the number of words appears.

15 . The system of claim 14 , further comprising deducing to which business line of a company each of the number of words is most related.