Content publisher recommender
Disclosed is a content publisher recommender system comprising: a server; a content database, configured within the server, within which are stored one or more channels associated with an end user, wherein the one or more channels stores at least one end user identification and a user historical database including a time log of the end user's activity, a log of search phrases used by the end user, a record of results identified on the search phrases; a ranking of the record of results, a record of which results the end user interacts with and a record of the format of the first clicked results from an end user wherein the search phrases are analysed using natural language processing to reduce the terms of the search phrases to their root form, the terms of the phrase are broken down into their part of speech and all keywords identified during natural language processing have stop words removed; and wherein considerations of the stored data and the analysis provides a ranking for searching to provide recommended content.
1. A content publisher recommender system comprising:
a. a server including a processor;
b. a content database, configured within the server, the content database storing data, associated with an end user, a associated with; user historical database including a time log of the end user's activity; associated with a log of search phrases used by the end user; associated with a record of results identified on the search phrases; associated with a record of which results the end user interacts with; associated with a record of the format of a set of first clicked results; associated with the average time a user views the results the user interacts with; and a ranking of the record of results;
wherein the ranking of the results is provided by processing of the data by the server and includes consideration of attributes associated with the record of results, the attributes comprising positive or negative attributes, positive attributes and longer average view times giving a higher ranking;
wherein the search phrases are processed by the server using natural language processing to reduce the terms of the search phrases to their root form, the terms of the phrase are broken down into their part of speech and all keywords identified during natural language processing have stop words removed;
wherein the ranking of results is used to provide a recommendation to a user on content.
2. The system according to claim 1 , wherein attributes are associated with the record of results, the attributes comprising a positive attribute for results that have more results than others.
3. The system according to claim 1 , wherein attributes are associated with the record of results, the attributes comprising a positive attribute for engagement for an extended period of time.
4. The system according to claim 1 , wherein attributes are associated with the record of results, the attributes comprising identification of the format of first clicked results.
5. The system according to claim 3 , wherein engagement for more than 30 seconds is considered positive.
6. The system according to claim 1 , wherein the analysis of search phrases includes lemmatizing the search phrases.