Document processing

1. A method for processing a text message to be sent by electronic mail (email) to a receiving address, said method comprising:

generating, by one or more processors of a computer system, a text message addressed to the receiving address using a communication tool;

analyzing, by the one or more processors, the text message using a semantic engine;

assigning a content score value to the text message for each content category of a plurality of content categories;

collecting, by the one or more processors, context data values relating to the text message and to a plurality of context categories, said context data values being metadata of previous historical messages exchanged with the receiving address;

determining, by the one or more processors, a context score value for each context category of the plurality of context categories by comparing the context data values with context data threshold values and determining, by the one or more processors, the context score values from only those context data values that exceed the context data threshold values, wherein said determining the context score value for each context category comprises computing, for each context category, the context score value as a function of a ratio of a total number of occurrences of a current context data value that exceeds the context data threshold values to a total number of occurrences of all context data values that exceed the context data threshold values;

determining, by the one or more processors, a content score value for each content category of the plurality of content categories by comparing the content score value of the text message for each content category of the plurality of content categories against content threshold values and determining the content score values from only those content data values that exceed the content data threshold values;

calculating, by the one or more processors, a difference factor value, wherein the plurality of content categories and the plurality of context categories contain n identical categories wherein n is at least 2, and wherein the difference factor is calculated by:

difference factor value=sqrt[Σ 1 n ((context score i −content score i ){circumflex over ( )}2)],

wherein sqrt=square root, context_score=the context score value for the context of the i-th identical category, content_score=the content score value for the content of the i-th identical category, and i=a counter for the n identical categories;

ascertaining, by the one or more processors, whether the difference factor value is greater than a specified difference factor threshold value;

if said ascertaining ascertains that the difference factor value is greater than the specified difference factor threshold value, then requesting, by the one or more processors, a confirmation before sending the text message to the receiving address, and if the confirmation is subsequently received then sending, by the one or more processors, the text message by electronic mail to the receiving address;

if said ascertaining ascertains that the difference factor value is not greater than the specified difference factor threshold value, then sending, by the one or more processors, the text message by electronic mail to the receiving address.

2. The method of claim 1 , wherein the semantic engine is using a repository of expressions that is extendable each time an unrecognized expression appears in the text message.

3. The method of claim 1 , wherein the plurality of context categories comprise at least one context category selected from the group consisting of at least one attribute value relating to the receiving address, day of week, time of day, type of network connection, receiving address from predetermined directory, receiving address from predetermined internet domain, previous text messages exchanged with the receiving address, and combinations thereof.

4. The method of claim 1 , wherein the communication tool is text based, and wherein the communication tool is a chat program, an email program, a short message service (SMS) program, a web log program, or a news group posting program.

5. The method of claim 1 , wherein said ascertaining ascertains that the difference factor value is greater than the specified difference factor threshold value, and wherein the confirmation is subsequently received.

6. The method of claim 1 , wherein said ascertaining ascertains that the difference factor value is not greater than the specified difference factor threshold value.

7. A computer program product, comprising one or more computer readable hardware storage devices having computer readable program code stored therein, said program code containing instructions executable by one or more processors of a computer system to implement a method for processing a text message to be sent by electronic mail (email) to a receiving address, said method comprising:

generating, by the one or more processors, a text message addressed to the receiving address using a communication tool;

analyzing, by the one or more processors, the text message using a semantic engine and assigning a content score value to the text message for each content category of a plurality of content categories;

collecting, by the one or more processors, context data values relating to the text message and to a plurality of context categories, said context data values being metadata of previous historical messages exchanged with the receiving address;

determining, by the one or more processors, a context score value for each context category of the plurality of context categories by comparing the context data values with context data threshold values and determining, by the one or more processors, the context score values from only those context data values that exceed the context data threshold values, wherein said determining the context score value for each context category comprises computing, for each context category, the context score value as a function of a ratio of a total number of occurrences of a current context data value that exceeds the context data threshold values to a total number of occurrences of all context data values that exceed the context data threshold values;

determining, by the one or more processors, a content score value for each content category of the plurality of content categories by comparing the content score value of the text message for each content category of the plurality of content categories against content threshold values and determining the content score values from only those content data values that exceed the content data threshold values;

calculating, by the one or more processors, a difference factor value, wherein the plurality of content categories and the plurality of context categories contain n identical categories, wherein n is at least 2, and wherein the difference factor is calculated by:

difference factor value=sqrt[Σ 1 n ((context score i −content score i ){circumflex over ( )}2)],

wherein sqrt=square root, context_score=the context score value for the context of the i-th identical category, content_score=the content score value for the content of the i-th identical category, and i=a counter for the n identical categories;

ascertaining, by the one or more processors, whether the difference factor value is greater than a specified difference factor threshold value;

if said ascertaining ascertains that the difference factor value is greater than the specified difference factor threshold value, then requesting, by the one or more processors, a confirmation before sending the text message to the receiving address, and if the confirmation is subsequently received then sending, by the one or more processors, the text message by electronic mail to the receiving address;

if said ascertaining ascertains that the difference factor value is not greater than the specified difference factor threshold value, then sending, by the one or more processors, the text message by electronic mail to the receiving address.

8. The computer program product of claim 7 , wherein said ascertaining ascertains that the difference factor value is greater than the specified difference factor threshold value, and wherein the confirmation is subsequently received.

9. The computer program product of claim 7 , wherein said ascertaining ascertains that the difference factor value is not greater than the specified difference factor threshold value.

10. A computer system, comprising one or more processors, one or more memories, and one or more computer readable hardware storage devices, said one or more hardware storage device containing program code executable by the one or more processors via the one or more memories to implement a method for processing a text message to be sent by electronic mail (email) to a receiving address, said method comprising:

generating, by the one or more processors, a text message addressed to the receiving address using a communication tool;

analyzing, by the one or more processors, the text message using a semantic engine and assigning a content score value to the text message for each content category of a plurality of content categories;

collecting, by the one or more processors; context data values relating to the text message and to a plurality of context categories, said context data values being metadata of previous historical messages exchanged with the receiving address;

determining, by the one or more processors, a context score value for each context category of the plurality of context categories by comparing the context data values with context data threshold values and determining, by the one or more processors, the context score values from only those context data values that exceed the context data threshold values, wherein said determining the context score value for each context category comprises computing, for each context category, the context score value as a function of a ratio of a total number of occurrences of a current context data value that exceeds the context data threshold values to a total number of occurrences of all context data values that exceed the context data threshold values;

determining, by the one or more processors, a content score value for each content category of the plurality of content categories by comparing the content score value of the text message for each content category of the plurality of content categories against content threshold values and determining the content score values from only those content data values that exceed the content data threshold values;

calculating, by the one or more processors, a difference factor value, wherein the plurality of content categories and the plurality of context categories contain n identical categories wherein n is at least 2, and wherein the difference factor is calculated by:

calculating, by the one or more processors, a difference factor value, wherein the plurality of content categories and the plurality of context categories contain n identical categories, wherein n is at least 2, and wherein the difference factor is calculated by:

difference factor value=sqrt[Σ 1 n ((context score i −content score i ){circumflex over ( )}2)],

wherein sqrt=square root, context_score=the context score value for the context of the i-th identical category, content_score=the content score value for the content of the i-th identical category, and i=a counter for the n identical categories;

ascertaining, by the one or more processors, whether the difference factor value is greater than a specified difference factor threshold value;

if said ascertaining ascertains that the difference factor value is greater than the specified difference factor threshold value, then requesting; by the one or more processors, a confirmation before sending the text message to the receiving address, and if the confirmation is subsequently received then sending, by the one or more processors, the text message by electronic mail to the receiving address;

if said ascertaining ascertains that the difference factor value is not greater than the specified difference factor threshold value, then sending, by the one or more processors, the text message by electronic mail to the receiving address.

11. The computer system of claim 10 , wherein said ascertaining ascertains that the difference factor value is greater than the specified difference factor threshold value, and wherein the confirmation is subsequently received.

12. The computer system of claim 10 , wherein said ascertaining ascertains that the difference factor value is not greater than the specified difference factor threshold value.