MEASURING SOCIAL MEDIA IMPACT FOR BRANDS

• US 20170262869A1
• Filed: 03/10/2016
• Published: 09/14/2017
• Est. Priority Date: 03/10/2016
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: JALALI, Fatemeh, LIANG, Xi, MASHFORD, Benjamin Scott, PERVIN, Shaila, SHERCHAN, Wanita
• Application Number:
  US15/066,076
• Publication Number:
  US 20170262869A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49

Abstract

To evaluate impact to a brand on social media, a computer is used to crawl through social media postings of social media services to select postings relating to one or more sponsored events. The selected postings are analyzed by computer to quantify keywords relating to particular brands. Images posted within the selected postings are also analyzed, using a pattern matching algorithm, to quantify depictions of the one or more brands within the images.

Claims

1. A method, comprising:

using one or more processors executing software stored on computer readable storage medium to;

crawl through social media postings of one or more social media services to select postings relating to one or more sponsored events;

analyze text posted within the selected postings to quantify keywords relating to one or more brands; and

analyze images posted within the selected postings to quantify, using a pattern matching algorithm, depiction of the one or more brands within the images.

2. The method of claim 1, wherein crawling is carried out using an API of the one or more social media services.

3. The method of claim 1, wherein the images analyzed are frames within a video posted within the selected postings.

4. The method of claim 1, further including using the one or more processors to analyze videos posted within the selected postings to quantify, using a pattern matching algorithm, depiction of the one or more brands within frames of the videos.

5. The method of claim 1, further including using the one or more processors to use the quantified keywords and depictions to determine an extent of brand impressions of the one or more brands in association with sponsoring the one or more events.

6. The method of claim 1, wherein the one or more events include different events, and the quantified keywords and depictions are analyzed using Tradeoff Analytics of IBM Watson Technology to determine events for sponsorship of the one or more brands in the future.

7. The method of claim 6, wherein the Tradeoff Analytics compares an extent of brand impressions of the one or more brands at the one or more events for historical incidences of the one or more events.

8. The method of claim 1, wherein the keywords analyzed include one or more hashtags corresponding to the one or more brands.

9. The method of claim 1, further including analyzing text includes analyzing a sentiment of the text as being in favor of, or not in favor of, the one or more brands.

10. The method of claim 1, further including using the processor to compare the quantified keywords and depictions among historical incidences of the one or more events in order to determine a value of future sponsorship of the one or more brands for the one or more events.

11. The method of claim 1, wherein images are analyzed in postings where there are no keywords in the posting relating to the one or more brands.

12. The method of claim 1, wherein no sponsorship payment was made to include the images within the selected postings.

13. The method of claim 1, wherein the postings were posted to Twitter by people not affiliated with the one or more brands or the sponsor.

14. The method of claim 1, wherein the postings were posted to a social media service selected from the group consisting of TWITTER, FACEBOOK, INSTAGRAM, and YOUTUBE, by people not affiliated with the one or more brands or the sponsor.

15. The method of claim 1, wherein the one or more processors are further used to analyze sound files posted within the selected postings to identify, using an audio pattern matching algorithm, sounds corresponding to the one or more brands within the sound files.

16. The method of claim 1, wherein the one or more processors are further used to analyze text of news feed postings relating to the one or more sponsored events for text containing keywords relating to the one or more brands.

17. The method of claim 1, wherein the one or more processors executing software function as a service on the Internet.

18. A computer program product for evaluating an impact to a brand, comprising:

a computer readable storage medium having program instructions, embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to;

crawl through social media postings of one or more social media services to select postings relating to one or more sponsored events;

analyze text posted within the selected postings to quantify keywords relating to one or more brands; and

analyze images posted within the selected postings to quantify, using a pattern matching algorithm, depiction of the one or more brands within the images.

19. A method for evaluating impact to a brand on social media, comprising:

using one or more processors executing software stored on computer readable storage medium to;

crawl through social media postings of one or more social media services to select social media user postings relating to one or more sponsored events using a predetermined list of events;

separate text, audio, video, and image data from the selected postings;

filter the separated data by one or more brands using a predetermined list of brands, by analyzing text to identify keywords within the separated data relating to one or more brands, and by analyzing images or video frames within the separated data to identify depictions of the one or more brands within the images; and

determine the social media impact of the one or more sponsored events by measuring an extent of the identified keywords and depictions in the social media postings relating to the one or more sponsored events.

20. The method of claim 19, further including using a remote tradeoff analytics service to use the measured extent of the identified keywords and depictions to inform a decision of a choice of events for sponsoring of the one or more brands in the future.