INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

• US 20150106080A1
• Filed: 05/01/2014
• Published: 04/16/2015
• Est. Priority Date: 10/10/2013
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: MIURA, Yasuhide, HATTORI, Keigo, OKUMA, Tomoko
• Granted Patent: US 9,244,910 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

An information processing apparatus includes a receiving unit, a determining unit, a first assigning unit, an extracting unit, a second assigning unit, a modeling unit, and an output unit. The receiving unit receives a target character string. The determining unit determines whether a sentiment character string is included in the received character string. A first assigning unit assigns a label corresponding to a sentiment character string to the character string when the sentiment character string is included, and assigns plural labels to the character string when no sentiment character string is included. The extracting unit extracts a word from the character string. The second assigning unit assigns to the extracted word a label which has been assigned to the character string that includes the word. The modeling unit performs supervised topic modeling for the character string. The output unit outputs a result of a process by the modeling unit.

Claims

1. An information processing apparatus comprising:

a receiving unit that receives a target character string;

a determining unit that determines whether or not a sentiment character string is included in the character string received by the receiving unit, based on a memory that stores a sentiment character string, which is a character string representing a sentiment, and a label representing the sentiment, the sentiment character string and the label being associated with each other;

a first assigning unit that assigns a label corresponding to a sentiment character string to the character string in a case where the determining unit has determined that the sentiment character string is included in the character string, and that assigns a plurality of label stored in the memory to the character string in a case where the determining unit has determined that no sentiment character string is included in the character string;

an extracting unit that extracts a word from the character string;

a second assigning unit that assigns to the word extracted by the extracting unit a label which has been assigned to the character string that includes the word;

a modeling unit that performs supervised topic modeling for the character string, based on the character string to which the label has been assigned by the second assigning unit, as supervisory information; and

an output unit that outputs a result of a process by the modeling unit.

2. The information processing apparatus according to claim 1,

wherein the memory stores a label which negates a sentiment as a label, and

wherein in a case where the determining unit has determined that a sentiment character string is included in the character string and a label corresponding to the sentiment character string is a label which negates a sentiment, the first assigning unit assigns a label representing a sentiment different from the negated sentiment to the character string.

3. The information processing apparatus according to claim 1, wherein the sentiment character string stored in the memory is a smiley.

4. The information processing apparatus according to claim 2, wherein the sentiment character string stored in the memory is a smiley.

5. The information processing apparatus according to claim 3, wherein the sentiment character string stored in the memory includes a word representing a sentiment.

6. The information processing apparatus according to claim 4, wherein the sentiment character string stored in the memory includes a word representing a sentiment.

7. An information processing method comprising:

receiving a target character string;

determining whether or not a sentiment character string is included in the received character string, based on storing a sentiment character string, which is a character string representing a sentiment, and a label representing the sentiment, the sentiment character string and the label being associated with each other;

assigning a label corresponding to a sentiment character string to the character string in a case where it has been determined that the sentiment character string is included in the character string, and assigning a plurality of stored labels to the character string in a case where it has been determined that no sentiment character string is included in the character string;

extracting a word from the character string;

assigning to the extracted word a label which has been assigned to the character string that includes the word;

performing supervised topic modeling for the character string, based on the character string to which the label has been assigned, as supervisory information; and

outputting a result of a process.

8. A non-transitory computer readable medium storing a program causing a computer to execute a process for information processing, the process comprising:

receiving a target character string;

determining whether or not a sentiment character string is included in the received character string, based on storing a sentiment character string, which is a character string representing a sentiment, and a label representing the sentiment, the sentiment character string and the label being associated with each other;

assigning a label corresponding to a sentiment character string to the character string in a case where it has been determined that the sentiment character string is included in the character string, and assigning a plurality of stored labels to the character string in a case where it has been determined that no sentiment character string is included in the character string;

extracting a word from the character string;

assigning to the extracted word a label which has been assigned to the character string that includes the word;

performing supervised topic modeling for the character string, based on the character string to which the label has been assigned, as supervisory information; and

outputting a result of a process.