際際滷

際際滷Share a Scribd company logo
Exploring Social Media Search Results
Rianne Kaptein


ECIR Industry Day
April 5th 2012 Barcelona
BACKGROUND OXYME


Fact Sheet                                           Clients


 Est. in 2007                                         Consumer Goods               FMCG


 Based in Amsterdam

 24 client staff (9 nationalities) and 350 social

  media analysts around the globe                                                 Chemicals


 13 languages covered by native speakers            Transport & Logistics


 125 projects completed at:
                                                                                 Other sectors
                                                       Dutch National Airport
       o     30 Multinational clients

       o     In 12 countries
                                                       Dutch National Railways
APPROACH | QUALITY DATA BY AUTOMATED & HUMAN ANALYSIS

                 Inhouse built             Human analysis                       Translate high
                  specialized               to remove not                      quality data into
                search software            relevant results                   actionable insights



Define a solid          Collect opinions   Smart analysis     Classify only       Analyze and
search strategy         with a webrobot                       relevant data       report


                                              Total results   WHERE

Search strategy                                               WHAT

                                                              WHO
Search period                               # Not relevant
                                                              MESSAGE

Search terms                                                  SENTIMENT
                        And thousands
                        more!                                 Etc.
                                               # Relevant
The Problem
SOCIAL MEDIA SEARCH TYPES



   Personal: What do my friends say about x?
   General: What does the world say about x?
   Commercial:
       What are people saying about my brand, product or campaign?
       What are people saying about my competitors?


 Relevant result:
 Oh delicious! I just got Orangina at Albert Heijn. Orangina and I are friends for life
SOCIAL MEDIA SEARCH CHARACTERISTICS



   The date and time of search results is important.
      Out of the temporal context, the meaning of the message might be
       lost
      The query can include temporal restrictions, e.g. monitor a product
       launch
   Ambiguity of search terms
   Many search results are short such as tweets, or Facebook status
    updates.
      Not a lot of noise in the text
   Recall is important, you want to know how many people talk about you.
      Large volumes of data
   You want to know who is talking and how influential their messages are.
      Identify promotors of your products
      Identify complaints
      Advertisements and spam
TWITTER SEARCH RESULTS
ICE ROCKET SEARCH RESULTS
FINCHLINE SEARCH & MONITORING TOOL
TuneIn
YET ANOTHER SEARCH ENGINE


Goal: First impression about the buzz around a brand
Exploit capabilities of human analysis: make it easy for the user to explore
and analyze the search results
Show basic statistics
Show differences over time
Show all results: raise awareness about what people will find when they
search for your company
TUNEIN
TUNEIN
TUNEIN
TWO DIMENSIONAL WORDCLOUDS




Two dimensions:
o Size of terms represents relative term frequency
o Colour of terms represents novelty of term

Instead of novelty other categorizations can be used as the second dimension
in the word cloud.

Categorizations can include :
 sentiment: positive vs. negative messages
 brands: messages mentioning "Braun" vs. messages mentioning "Gillette"
POSITIVE VS. NEGATIVE COFFEE MACHINE MESSAGES
WARNING SIGN 1




Rubbish in, rubbish out!
Be careful with your categorizations.

If too many messages are not classified into the correct category, the quality of
the wordcloud will degrade.

Since in the interface it's easy to go back to the original message, users will not
trust the system if they see too many misclassified messages
COMPARING DELONGHI AND SAECO BY OCCURRENCES IN TEXT
COMPARING TAGGED NEGATIVE POSTS SAECO AND DELONGHI
WARNING SIGN 2




Be careful with small result sets:

If at least one of the two categories only consists of a few messages (e.g. less
than 25) the statistics on which the wordclouds are based are not so reliable

Think about your minimum sample size!
OTHER POINTS OF ATTENTION



   Words can have multiple meanings


 Be clear on the fact it is an automatically generated summary


   Heavily retweeted messages can have a large influence on the wordcloud
CONCLUSIONS




Wordclouds are a great search interface element for social media search

 Navigational aid:
Easy drilldown on search results

 Summary of large number of search results
Short, to the point messages
Thank you!
             www.oxyme.com
             Cronenburg 150
             1081 GN Amsterdam
             tel: +31 20 625 000 5
             e-mail: cu@oxyme.com

More Related Content

Exploring Social Media Search Results

  • 1. Exploring Social Media Search Results Rianne Kaptein ECIR Industry Day April 5th 2012 Barcelona
  • 2. BACKGROUND OXYME Fact Sheet Clients Est. in 2007 Consumer Goods FMCG Based in Amsterdam 24 client staff (9 nationalities) and 350 social media analysts around the globe Chemicals 13 languages covered by native speakers Transport & Logistics 125 projects completed at: Other sectors Dutch National Airport o 30 Multinational clients o In 12 countries Dutch National Railways
  • 3. APPROACH | QUALITY DATA BY AUTOMATED & HUMAN ANALYSIS Inhouse built Human analysis Translate high specialized to remove not quality data into search software relevant results actionable insights Define a solid Collect opinions Smart analysis Classify only Analyze and search strategy with a webrobot relevant data report Total results WHERE Search strategy WHAT WHO Search period # Not relevant MESSAGE Search terms SENTIMENT And thousands more! Etc. # Relevant
  • 5. SOCIAL MEDIA SEARCH TYPES Personal: What do my friends say about x? General: What does the world say about x? Commercial: What are people saying about my brand, product or campaign? What are people saying about my competitors? Relevant result: Oh delicious! I just got Orangina at Albert Heijn. Orangina and I are friends for life
  • 6. SOCIAL MEDIA SEARCH CHARACTERISTICS The date and time of search results is important. Out of the temporal context, the meaning of the message might be lost The query can include temporal restrictions, e.g. monitor a product launch Ambiguity of search terms Many search results are short such as tweets, or Facebook status updates. Not a lot of noise in the text Recall is important, you want to know how many people talk about you. Large volumes of data You want to know who is talking and how influential their messages are. Identify promotors of your products Identify complaints Advertisements and spam
  • 9. FINCHLINE SEARCH & MONITORING TOOL
  • 11. YET ANOTHER SEARCH ENGINE Goal: First impression about the buzz around a brand Exploit capabilities of human analysis: make it easy for the user to explore and analyze the search results Show basic statistics Show differences over time Show all results: raise awareness about what people will find when they search for your company
  • 15. TWO DIMENSIONAL WORDCLOUDS Two dimensions: o Size of terms represents relative term frequency o Colour of terms represents novelty of term Instead of novelty other categorizations can be used as the second dimension in the word cloud. Categorizations can include : sentiment: positive vs. negative messages brands: messages mentioning "Braun" vs. messages mentioning "Gillette"
  • 16. POSITIVE VS. NEGATIVE COFFEE MACHINE MESSAGES
  • 17. WARNING SIGN 1 Rubbish in, rubbish out! Be careful with your categorizations. If too many messages are not classified into the correct category, the quality of the wordcloud will degrade. Since in the interface it's easy to go back to the original message, users will not trust the system if they see too many misclassified messages
  • 18. COMPARING DELONGHI AND SAECO BY OCCURRENCES IN TEXT
  • 19. COMPARING TAGGED NEGATIVE POSTS SAECO AND DELONGHI
  • 20. WARNING SIGN 2 Be careful with small result sets: If at least one of the two categories only consists of a few messages (e.g. less than 25) the statistics on which the wordclouds are based are not so reliable Think about your minimum sample size!
  • 21. OTHER POINTS OF ATTENTION Words can have multiple meanings Be clear on the fact it is an automatically generated summary Heavily retweeted messages can have a large influence on the wordcloud
  • 22. CONCLUSIONS Wordclouds are a great search interface element for social media search Navigational aid: Easy drilldown on search results Summary of large number of search results Short, to the point messages
  • 23. Thank you! www.oxyme.com Cronenburg 150 1081 GN Amsterdam tel: +31 20 625 000 5 e-mail: cu@oxyme.com