Apparatus, and associated method, for detecting fraudulent text message
View Patent ↗An apparatus, and an associated method, detects spam and other fraudulent messages sent to a recipient station. The textual portion of a received message is analyzed to determine whether the message includes errors made by non-native language speakers when authoring a text message. A text analysis engine analyzes the text using rules sets that identify grammatical errors made by non-native language speakers, usage errors made by non-native language speakers, and other errors.
1. An apparatus for facilitating detection that a received text message forms a fraudulent message, said apparatus comprising:
a text analyzer configured to analyze a textual portion of the received text message to detect non-native language content; and
a detector configured to detect, based upon analysis made by said text analyzer, at least an indicia indicative of whether the received message forms a fraudulent message;
in which the detector calculates a likelihood value indicative of a likelihood that the received text message forms a fraudulent message via a weighted function of the textual portion of the text message, non-native grammatical errors therein, non-native usage errors therein, and general errors therein; wherein the detector further calculates weighting factors associated with a number of variables within the weighting function.
2. The apparatus of claim 1 further comprising a grammatical rules error set, said grammatical rules error set identifying non-native language syntax.
3. The apparatus of claim 2 wherein said text analyzer is configured to access the grammatical rules set and to use the grammatical rules set pursuant to the analysis made by said text analyzer.
4. The apparatus of claim 2 wherein the grammatical rules error set comprises rules associated with grammatical errors made by non-native language speakers.
5. The apparatus of claim 2 wherein the grammatical rules error set comprises rules associated with usage errors made by non-native language speakers.
6. The apparatus of claim 2 wherein the grammatical rules error set comprises rules associated with general syntactical errors.
7. The apparatus of claim 1 , wherein the likelihood value is calculated using a weighted textual portion weighted by a first weighting factor, weighted non-native grammatical errors weighted by a second weighting factor, weighted non-native usage, weighted by a third weighting factor, weighted general errors, weighted by a fourth weighting factor.
8. The apparatus of claim 7 wherein the first, second, third, and fourth weighting factors are unequal values.
9. The apparatus of claim 1 further comprising an alerter configured to generate an alert to alert detection by said detector of indicia indicative that the received message forms a fraudulent message.
10. A junk mail detector for detecting when a received email is a junk email, said junk mail detector comprising:
an analyzer configured to analyze the received email for presence therein of content typically formed by non-native-language authors; and
a warning generator configured to generate a warning display prior to display of the received email if analysis made by said analyzer indicates the received email to be junk email;
in which the junk mail detector calculates a likelihood value indicative of a likelihood that the received email is a junk email by calculating a number of weighting factors such that the likelihood value is calculated using a function of a textual portion of the email weighted by a first weighting factor, non-native grammatical errors in the email weighted by a second weighting factor, non-native usage in the email weighted by a third weighting factor, and general errors in the email weighted by a fourth weighting factor.
11. The junk mail detector of claim 10 , in which the first, second, third, and fourth weighting factors are unequal values.
12. A method for facilitating detection that a received text message forms a fraudulent message, said method comprising:
analyzing a textual portion of the received text message to detect non-native language content; and
detecting, based upon analysis made during said analyzing, at least an indicia indicative of whether the received message forms a fraudulent message,
in which detecting an indicia indicative of whether the received message forms a fraudulent message further comprises calculating a likelihood value indicative of a likelihood that the received text message is a fraudulent text message via a weighted function of the textual portion, non-native grammatical errors therein, non-native usage errors therein, and general errors therein; in which the likelihood value is calculated by calculating weighting factors associated with a number of variables within the weighted function.
13. The method of claim 12 further comprising generating a warning if the indicia detected during said analyzing indicates that the received message forms a fraudulent message.
14. The method of claim 13 further comprising providing for selection of whether to display the received message.
15. The method of claim 12 wherein said analyzing comprises accessing a grammatical rules error set and comparing error rules therein with the received message.
16. The method of claim 15 wherein the grammatical rules error set comprises rules identifying non-native language syntax.
17. The method of claim 15 wherein the grammatical rules error set comprises rules associated with grammatical errors made by non-native language speakers.
18. The method of claim 15 wherein the grammatical rules error set comprises rules associated with usage errors made by non-native language speakers.