US 12,073,444 B2
Method and system for programmatic analysis of consumer reviews
Gaston L'Huillier, San Francisco, CA (US); Francisco Jose Larrain, Palo Alto, CA (US); Hernan Enrique Arroyo Garcia, Mountain View, CA (US); Juzheng Li, Fremont, CA (US); Daniel Langdon, Las Condes (CL); Jonathan Esterhazy, San Francisco, CA (US); Srinivasa Raghavan Vedanarayanan, Sunnyvale, CA (US); Shawn Jeffery, Burlingame, CA (US); Feras Karablieh, Issaquah, WA (US); Bhupesh Bansal, Sunnyvale, CA (US); Dor Levi, San Francisco, CA (US); and Amit Koren, Chicago, IL (US)
Assigned to Bytedance Inc., Wilmington, DE (US)
Filed by GROUPON, INC., Chicago, IL (US)
Filed on Dec. 23, 2020, as Appl. No. 17/132,915.
Application 17/132,915 is a continuation of application No. 15/659,138, filed on Jul. 25, 2017, granted, now 10,909,585.
Application 15/659,138 is a continuation of application No. 15/073,486, filed on Mar. 17, 2016, granted, now 9,741,058, issued on Aug. 22, 2017.
Application 15/073,486 is a continuation of application No. 14/727,852, filed on Jun. 1, 2015, granted, now 9,317,566, issued on Apr. 19, 2016.
Claims priority of provisional application 62/033,090, filed on Aug. 4, 2014.
Claims priority of provisional application 62/030,549, filed on Jul. 29, 2014.
Claims priority of provisional application 62/018,456, filed on Jun. 27, 2014.
Prior Publication US 2021/0256574 A1, Aug. 19, 2021
Int. Cl. G06Q 30/0282 (2023.01); G06F 16/2455 (2019.01); G06F 16/2457 (2019.01); G06F 16/951 (2019.01); G06N 20/00 (2019.01); G06Q 30/02 (2023.01)
CPC G06Q 30/0282 (2013.01) [G06F 16/2455 (2019.01); G06F 16/24578 (2019.01); G06F 16/951 (2019.01); G06N 20/00 (2019.01); G06Q 30/0281 (2013.01)] 25 Claims
OG exemplary drawing
 
1. An apparatus for programmatically parsing and analyzing a consumer review extracted from an Internet website, wherein the consumer review is associated with a commercial entity or with a commercial object, the apparatus comprising:
a processor configured to programmatically access, via a networked device, the consumer review; and
a consumer review processing engine programmed to: (a) programmatically identify an attribute descriptor set from the consumer review, and (b) programmatically generate a consumer review sentiment score associated with the consumer review, wherein programmatically generating the consumer review sentiment score comprises:
using a natural language processing engine to:
programmatically parse the consumer review into a sentence set;
programmatically parse each sentence of the sentence set into a word set; and
for each word in each word set, programmatically generate a word part of speech and a word context of use; and
using a sentiment scoring engine to:
for each word in each word set, programmatically generate a word sentiment score, wherein programmatically generating the word sentiment score comprises: generating (1) a word polarity score using the word part of speech and the word context of use, (2) a word negation score, and (3) a word intensity score;
for each sentence in the sentence set, programmatically generating a sentence sentiment score using a machine learning algorithm trained based on word sentiment scores, word polarity scores, word intensity scores, and word negation scores associated with each respective sentence; and
programmatically generate the consumer review sentiment score by aggregating the sentence sentiment scores for each sentence of the sentence set;
programmatically storing the attribute descriptor set, the sentence sentiment scores, and the consumer review sentiment score to a non-transitory computer-readable storage device in association with the commercial entity or the commercial object;
determine one or more attribute descriptors of the attribute descriptor set that are relevant to a consumer associated with a computing device; and
cause the networked device to transmit one or more computer-executable instructions to the computing device, the one or more computer-executable instructions being programmed to cause the computing device to visually display the one or more attribute descriptors and the consumer review sentiment score in association with the commercial entity or the commercial object.