Method and system relating to sentiment analysis of electronic content

Abstract

Users receive information which must be filtered, processed, analysed, reviewed, consolidated and distributed or acted upon. Prior art tools automatically processing content to assign sentiment to the content are ineffective as essential aspects such as context are not considered. Embodiments of the invention provide automatic contextual based sentiment classification of content in terms of both sentiments expressed and their intensity. Further a content set is analysed to rapidly establish an “at-a-glance” type assessment of the key topics/themes present within the content set and sentimentally annotate each. Importantly embodiments of the invention also provide for a user to establish the basis for the sentiment associated with an item of or set of content, i.e. make it explainable. Further embodiments of the invention provide for the establishment of psychological tone to sentiments where the sentiments and psychological tones to be tuned from the context or domain of the content.

What is claimed is: 
     
         1 . A system comprising:
 a server connected to a global communications network;   a non-volatile non-transitory memory coupled to the server storing:
 a database stored within the non-volatile, non-transitory memory comprising a plurality of items of electronic content; and 
 computer software instructions stored within the non-volatile non-transitory memory for execution by the server, the computer software instructions when executed automatically generating an overall sentiment count for an item of electronic content of the plurality of items of electronic content via a process comprising the steps of:
 retrieving from the non-volatile non-transitory memory a plurality of predetermined portions of an item of electronic content of the plurality of items of electronic content; 
 parsing each retrieved predetermined portion of the item of electronic content to establish a plurality of positive sentiment terms; 
 counting occurrences of a positive sentiment term of the plurality of positive sentiment terms within that predetermined portion of the item of electronic content to establish a positive sentiment count for that predetermined portion of the item of electronic content; 
 parsing each retrieved predetermined portion of the item of electronic content to establish a plurality of negative sentiment terms; 
 counting occurrences of a negative sentiment term of the plurality of negative sentiment terms within the predetermined portion of the item of electronic content to establish a negative sentiment count for that predetermined portion of the item of electronic content; 
 establishing a portion weighting for each retrieved predetermined portion of the item of electronic content; 
 multiplying each of the positive sentiment count and the negative sentiment count for a predetermined portion of the item of electronic content by the portion weighting for that retrieved predetermined portion to establish a portion weighted positive sentiment for that predetermined portion of the item of electronic content and a portion weighted negative sentiment for that predetermined portion of the item of electronic content; 
 determining a sentiment label to associate with the item of electronic content in dependence upon at least one of the occurrences of the positive sentiment term and occurrences of the negative sentiment term within each predetermined portion of the item of content; and 
 summing all the portion weighted positive sentiments and the portion weighted negative sentiments for the item of electronic content of the plurality of items of electronic content to generate an overall sentiment count for an item of electronic content. 
 
   
     
     
         2 . The system according to  claim 1 , wherein
 each positive sentiment term of the plurality of positive sentiment terms has an associated positive intensity level;   each negative sentiment term of the plurality of negative sentiment terms has an associated negative intensity level.   
     
     
         3 . The system according to  claim 2 , wherein
 counting occurrences of the positive sentiment terms of the plurality of positive sentiment terms is achieved by:
 determining a number of occurrences for each positive sentiment term; 
 multiplying the number of occurrences for each positive sentiment term by its respective intensity level to generate a weighted occurrence count; 
 summing the resulting weighting occurrence counts for the plurality of positive sentiment counts to generate the positive sentiment count; and 
   counting occurrences of the negative sentiment terms of the plurality of negative sentiment terms is achieved by:
 determining a number of occurrences for each negative sentiment term; 
 multiplying the number of occurrences for each negative sentiment term by its respective intensity level to generate a weighted occurrence count; 
 summing the resulting weighting occurrence counts for the plurality of negative sentiment counts to generate the negative sentiment count. 
   
     
     
         4 . The method according to  claim 1 , further comprising:
 associating a domain with the item of electronic content of the plurality of items of electronic content; and   establishing a sentiment lexicon of a plurality of sentiment lexicons in dependence upon at least the domain; wherein   the sentiment lexicon defines the plurality of positive sentiment terms and the plurality of negative sentiment terms.   
     
     
         5 . The system according to  claim 1 , wherein
 determining the sentiment label is at least one of:
 also dependent upon the imbalance between the counts of occurrences of the positive sentiment term and negative sentiment term; and 
 selecting a sentiment label that is not one of either the positive sentiment term or negative sentiment term used in establishing the occurrences. 
   
     
     
         6 . The system according to  claim 1 , wherein
 generating the sentiment label is achieved in dependence upon at least one the difference, the sum, the ratio of the occurrences of the positive sentiment term and occurrences of the negative sentiment term, the positive sentiment term, and the negative sentiment term.   
     
     
         7 . The system according to  claim 1 , wherein
 generating a psychological tone qualification in dependence upon at least one the difference, the sum, the ratio of the occurrences of the positive sentiment term and occurrences of the negative sentiment term, the positive sentiment term, and the negative sentiment term.   
     
     
         8 . The system according to  claim 1 , further comprising:
 counting occurrences of the remaining positive sentiment terms of the plurality of positive sentiment terms within that predetermined portion of the item of electronic content to establish positive sentiment counts for each remaining positive sentiment terms of the plurality of positive sentiment terms within that predetermined portion of the item of electronic content;   counting occurrences of the remaining negative sentiment terms of the plurality of negative sentiment terms within that predetermined portion of the item of electronic content to establish negative sentiment counts for each remaining negative sentiment terms of the plurality of negative sentiment terms within that predetermined portion of the item of electronic content;   summing all positive sentiment counts for that predetermined portion of the item of electronic content to generate a total positive sentiment count for that predetermined portion of the item of electronic content;   summing all negative sentiment counts for that predetermined portion of the item of electronic content to generate a total negative sentiment count for that predetermined portion of the item of electronic content;   establishing a sentiment label to associate with the item of electronic content of the plurality of items of electronic content in dependence upon the total positive count for that predetermined portion of the item of electronic content and the total negative count for that predetermined portion of the item of electronic content.   
     
     
         9 . The system according to  claim 6 , further comprising:
 generating a psychological tone qualification in dependence upon at least one of the distribution of occurrences of all positive sentiment terms of the plurality of positive sentiment terms and the distribution of occurrences of all negative sentiment terms of the plurality of the negative sentiment terms.   
     
     
         10 . The system according to  claim 1 , further comprising:
 associating a domain with the item of electronic content of the plurality of items of electronic content; and   determining a sentiment to associate to an item of electronic content in dependence upon at least the domain and the sentiment label.   
     
     
         11 . The system according to  claim 1 , wherein
 the item of electronic content was established in response to a search performed by a user using an Internet search engine; wherein   the item of electronic content is selected from the group comprising documents, images, spreadsheets, databases, audiovisual data, multimedia data, encrypted data, SMS messages, social media data, data formatted according to a markup language, and information formatted according to a portable document format.   
     
     
         12 . The system according to  claim 1 , further comprising
 performing the process for the plurality of items of electronic content;   summing the occurrences of the positive sentiment term and occurrences of the negative sentiment term for the plurality of items of electronic content; and   generating an overall sentiment for the plurality of items of electronic content in dependence upon the summed occurrences of the positive sentiment term and summed occurrences of the negative sentiment term for the plurality of items of electronic content; wherein   the item of electronic content is selected from the group comprising documents, images, spreadsheets, databases, audiovisual data, multimedia data, encrypted data, SMS messages, social media data, data formatted according to a markup language, and information formatted according to a portable document format.   
     
     
         13 . The system according to  claim 1 , further comprising
 performing the process for the plurality of items of electronic content;   summing the occurrences of the positive sentiment term and occurrences of the negative sentiment term for the plurality of items of electronic content; and   generating an overall sentiment for the plurality of items of electronic content in dependence upon the summed occurrences of the positive sentiment term and summed occurrences of the negative sentiment term for the plurality of items of electronic content.   
     
     
         14 . The system according to  claim 1 , wherein
 the predetermined portions of the item of electronic content are established in dependence upon at least one of a template and a form associated with the item of electronic content.   
     
     
         15 . The system according to  claim 1 , wherein
 the predetermined portions of the item of electronic content are established in dependence upon a class of electronic content associated with the item of electronic content, wherein   the class of electronic content is selected from the group comprising electronic mail, a news article, a blog post, a social media post, a forum comment, a stock report, a news cast, a web page or an item of electronic content generated by an editorial process.   
     
     
         16 . The system according to  claim 1 , wherein
 the item of electronic content stored within the memory of the computer system is selected by a process comprising one of:
 a manual selection by a user of a software application in execution upon a computer system connected to the global communications network; 
 automatically by a software application in execution upon a computer system connected to the global communications network; and 
 automatically by a software application in execution upon a remote computer system connected to the global communications network associated with a third-party service subscribed to by a user. 
   
     
     
         17 . The system according to  claim 1 , further comprising
 periodically and automatically selecting at a predetermined frequency at least one of the item of electronic content and the plurality of items of electronic content from a set of electronic documents associated with one or more sources of electronic content connected to the global communications network; and   transmitting the results of the sentiment analysis from the server to an electronic device associated with a user which is connected to the global communications network.   
     
     
         18 . The system according to  claim 1 , further comprising
 periodically and automatically selecting at a predetermined frequency at least one of the item of electronic content and the plurality of items of electronic content from a set of electronic documents associated with one or more sources of electronic content connected to the global communications network;   automatically processing at the server the set of electronic documents to establish at least one of a core concept and a set of core concepts; and   transmitting the results of the sentiment analysis together with the established at least one of the core concept and the set of core concepts from the server to an electronic device associated with a user which is connected to the global communications network.   
     
     
         19 . A system comprising:
 an electronic device associated with a user executing a software application relating to establishing a sentiment count of an item of electronic content; wherein   the sentiment of the item of electronic content is acquired from a remote server connected to the electronic device via a global communications network; and   the remote server comprises a database stored within a non-volatile, non-transitory memory comprising a plurality of items of electronic content and computer software instructions stored within the non-volatile non-transitory memory for execution by the server, the computer software instructions when executed automatically generating an overall sentiment count for an item of electronic content of the plurality of items of electronic content via a process comprising the steps of:
 retrieving from the non-volatile non-transitory memory a plurality of predetermined portions of an item of electronic content of the plurality of items of electronic content; 
 parsing each retrieved predetermined portion of the item of electronic content to establish a plurality of positive sentiment terms; 
 counting occurrences of a positive sentiment term of the plurality of positive sentiment terms within that predetermined portion of the item of electronic content to establish a positive sentiment count for that predetermined portion of the item of electronic content; 
 parsing each retrieved predetermined portion of the item of electronic content to establish a plurality of negative sentiment terms; 
 counting occurrences of a negative sentiment term of the plurality of negative sentiment terms within the predetermined portion of the item of electronic content to establish a negative sentiment count for that predetermined portion of the item of electronic content; 
 establishing a portion weighting for each retrieved predetermined portion of the item of electronic content; 
 multiplying each of the positive sentiment count and the negative sentiment count for a predetermined portion of the item of electronic content by the portion weighting for that retrieved predetermined portion to establish a portion weighted positive sentiment for that predetermined portion of the item of electronic content and a portion weighted negative sentiment for that predetermined portion of the item of electronic content; 
 determining a sentiment label to associate with the item of electronic content in dependence upon at least one of the occurrences of the positive sentiment term and occurrences of the negative sentiment term within each predetermined portion of the item of content; and 
 summing all the portion weighted positive sentiments and the portion weighted negative sentiments for the item of electronic content of the plurality of items of electronic content to generate an overall sentiment count for an item of electronic content. 
   
     
     
         20 . The system according to  claim 19 , wherein
 the item of electronic content stored within the memory of the remote server is selected by a process comprising one of:
 a manual selection by the user via the software application; 
 automatically by the software application; and 
 automatically by another software application in execution upon a remote computer system connected to the global communications network associated with a third-party service subscribed to by the user.