Checking documents for spelling and/or grammatical errors and/or providing recommended words or phrases based on patterns of colloquialisms used among users in a social network

• US 9,998,553 B2
• Filed: 06/17/2014
• Issued: 06/12/2018
• Est. Priority Date: 09/12/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Banatwala, Mustansir, Brooks, David A., Russo, Joseph A.
• Primary Examiner(s): Rostami, Mohammad S
• Application Number:
  US14/306,740
• Publication Number:
  US 20150074172A1
• Time in Patent Office: 1,456 Days
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

A method, system and computer program product for checking documents using colloquialisms. Colloquialisms used in messages by users in a social network are tracked. The relationships (e.g., co-worker) between the senders and recipients of these messages are identified. A social graph is then generated to depict the relations between the users in the social network based on these identified relationships. Furthermore, usage patterns of colloquialisms (e.g., a particular colloquialism is used only with close friends as opposed to co-workers) are formulated. A rule set is generated using the social graph and formulated usage patterns. By using the rule set to check documents, documents may be more accurately checked for spelling and/or grammatical errors by taking into consideration the appropriate usage of colloquialisms based on the context (e.g., communicating with a friend). Furthermore, alternative words or phrases may be appropriately recommended based on the context using such a rule set.

Claims

1. A method for checking documents using colloquialisms, the method comprising:

tracking colloquialisms used in messages by users in a social network;

identifying relationships between senders and recipients of said messages using said colloquialisms;

generating a social graph to depict relations between said users in said social network based on said identified relationships;

formulating usage patterns of said colloquialisms among said users of said social graph;

generating a rule set based on said social graph and said usage patterns of said colloquialisms among said users of said social graph; and

reviewing, by a processor, a document using said generated rule set.

2. The method as recited in claim 1 further comprising:

receiving said document to be reviewed for spelling and/or grammatical errors and/or for offering alternative words or phrases.

3. The method as recited in claim 1 further comprising:

reviewing said document for spelling and/or grammatical errors and/or for making contextual relevant recommendations using said generated rule set.

4. The method as recited in claim 1, wherein said usage patterns of said colloquialisms are based on a frequency of collaboration between said senders and recipients of said messages using said colloquialisms.

5. The method as recited in claim 1, wherein said usage patterns of said colloquialisms are based on a degree of separation between said senders and recipients of said messages using said colloquialisms.

6. The method as recited in claim 1, wherein said usage patterns of said colloquialisms are based on occurrences of said colloquialisms among other users in said social network.

7. The method as recited in claim 1, wherein said usage patterns of said colloquialisms are based on a type of online community said messages using said colloquialisms are posted.