| 摘要 |
A system, methods and user interface are disclosed for determining the connotation or sentiment type of a text unit comprising multiple terms and with a grammatical structure, such as subject+verb, verb+object, adjective+noun, noun+noun, noun+preposition+noun, and for highlighting or extracting such text units. The connotation or sentiment type of the text unit is determined by applying context rules where the context of the grammatical structure may change the inherent or default connotations of individual terms in the text unit. The methods provide a solution to the challenge of correctly or accurately determining the sentiment type of various linguistic structures under different context, and to the simplistic approach of using the inherent connotation of individual terms for the linguistic structure containing such terms, and highlighting only such terms without considering the contextual effects. |
| 主权项 |
1. A method implemented on a computer comprising a processor, and for performing actions on a multi-term text unit based on a derived semantic attribute or attribute value, the method comprising:
receiving a text content comprising multiple text units, each text unit comprising at least a portion of a phrase or a sentence consisting of multiple terms, each term comprising a word or a phrase in a language; identifying, in the text content, a text unit, wherein the text unit comprises a first term and a second term, wherein neither the first term nor the second term includes a grammatically defined negator or negation word; obtaining a derived semantic attribute or attribute value for the text unit as a whole based on the first term and the second term; and performing an action on the text unit based on the derived semantic attribute or attribute value, wherein the action includes extracting the text unit for display or storage, marking the text unit for display in a format that is different from the display format of the text elements adjacent to the text unit in the text content, or displaying the text unit in a format that is different from the display format of the text elements adjacent to the text unit in the text content; wherein the steps for obtaining the derived semantic attribute or attribute value for the text unit as a whole include the following: receiving a name or description of a semantic attribute, wherein the embodiment of the semantic attribute includes an attribute name or description, an attribute type or attribute value, wherein the semantic attribute comprises a first value and a second value each representing a meaning carried by a term in the language, wherein an example of the semantic attribute comprises a sentiment or opinion, and when the semantic attribute is a sentiment or opinion, each of the first value and the second value is either a positive value or a negative value, but not a neutral value; identifying the first term in the text unit, wherein the first term is associated with the first value; identifying the second term in the text unit, wherein the second term is associated with the second value; determining the derived semantic attribute or attribute value for the text unit as a whole based on the first term and the second term, and the first value and the second value. |
