1 Blog Mining – Market Research made easy? Bettina Berendt, K.U.Leuven, .

1

Blog Mining – Market Research made easy?

Bettina Berendt, K.U.Leuven, www.berendt.de

Blog Mining – Market Research made easy?

Bettina Berendt, K.U.Leuven, www.berendt.de

2

About me ...

3

Motivation / Excecutive summary

Dem Volk aufs Maul sehen :

4

Agenda

Concepts

The representativeness challenge

Text mining: first steps

Text mining: going deeper

Closing the loop: from blogs to blogs

From “online buzz“ to text mining

So ...

5

Agenda

Concepts






So ...

6

What‘s a blog?

a (more or less) frequently updated publication on the Web, sorted in (usually reverse) chronological order of the constituent blog posts.

The content may reflect any interests including personal, journalistic or corporate.

Usually textual, but multimedia forms exist (photoblog, vblog, …)

7

Blogs and other social media (“Web 2.0“)

Blogs(e.g., Livejournal; Huffington Post)Sharing / linking by:Hyperlinks, comments, blogroll, trackback links

Social network sites(e.g., MySpace)

Microblogging(e.g., Twitter)

Wikis(e.g., Wikipedia)

“Annotation platforms“(e.g., del.icio.us)

8

Blogs and other social media,and some of their origins in older media

Blogs(e.g., Livejournal; Huffington Post)Sharing / linking by:Hyperlinks, comments, blogroll, trackback links

Diaries (Often political) journalism PR; press releases

Social network sites(e.g., MySpace)

Dating sites

Chatrooms

Microblogging(e.g., Twitter)

Wikis(e.g., Wikipedia)

Computer-supportedcooperative work

“Annotation platforms“(e.g., del.icio.us)

Bookmarks www.dmoz.org

Usenet

9

What‘s market research?

identification, collection, analysis, and dissemination of information

for the purpose of assisting management in decision making related to the identification and solution of problems and opportunities in marketing

10

Traditional methods of (consumer) market research

Based on questioning: Focus groups, surveys, questionnaires, ...

Based on observations: Ethnographic studies - observe social phenomena in their natural

setting - observations can occur cross-sectionally or longitudinally - examples include product-use analysis and computer cookie traces.

Experimental techniques - create a quasi-artificial environment to try to control spurious factors, then manipulates at least one of the variables - examples include purchase laboratories and test markets

11

Agenda

Concepts






So ...

12

Capturing “online buzz“Capturing “online buzz“:Bursty communication actitivies

13

Comparing search volume, news and blogs

14

The idea of text mining ...

... is to go beyond frequency-counting

... is to go beyond the search-for-documents framework

... is to find patterns (of meaning) within and across documents

(yes, there is text mining behind some of the things the above tools do!)

15

The steps of text mining

1. Application understanding

2. Corpus generation

3. Data understanding

4. Text preprocessing

5. Search for patterns / modelling

Topical analysis

Sentiment analysis / opinion mining

6. Evaluation

7. Deployment

16

Agenda

Concepts






So ...

17

Application understanding; Corpus generation

What is the question?

What is the context?

What could be interesting sources, and where can they be found?

Crawl

Use a search engine and/or archive Google blogs search

Technorati

Blogdigger

...

18

Preprocessing (1)

Data cleaning

Goal: get clean ASCII text

Remove HTML markup*, pictures, advertisements, ...

Automate this: wrapper induction

* Note: HTML markup may carry information too (e.g., <b> or <h1> marks something important), which can be extracted! (Depends on the application)

19

Preprocessing (2)

Further text preprocessing Goal: get processable lexical / syntactical units Tokenize (find word boundaries) Lemmatize / stem

ex. buyers, buyer buyer / buyer, buying, ... buy

Remove stopwords Find Named Entities (people, places, companies, ...); filtering Resolve polysemy and homonymy: word sense disambiguation;

“synonym unification“ Part-of-speech tagging; filtering of nouns, verbs, adjectives, ... ...

Most steps are optional and application-dependent! Many steps are language-dependent; coverage of non-English varies Free and/or open-source tools or Web APIs exist for most steps

20

Preprocessing (3)

Creation of text representation

Goal: a representation that the modelling algorithm can work on

Most common forms: A text as

a set or (more usually) bag of words / vector-space representation: term-document matrix with weights reflecting occurrence, importance, ...

a sequence of words

a tree (parse trees)

21

An important part of preprocessing:Named-entity recognition (1)

22

An important part of preprocessing:Named-entity recognition (2)

Technique: Lexica, heuristic rules, syntax parsing

Re-use lexica and/or develop your own

configurable tools such as GATE

A challenge: multi-document named-entity recognition

See proposal in Subašić & Berendt (Proc. ICDM 2008)

23

The simplest form of content analysis is based on NER

Berendt, Schlegel und KochIn Zerfaß et al. (Hrsg.) Kommunikation, Partizipation und Wirkungen im Social Web, 2008

24

Agenda

Concepts






So ...

25

Feldman et al., Proc. ICDM 2007

More about named entities: co-occurrence

Source:Discussion boards similar to blogs,but (more) clearly communication-related

26

Co-occurrence of brands and attributes

Feldman et al., Proc. ICDM 2007

27

Recall “Michelle Obama“

Google Trends, Blogpulse etc. associate documents / document sets with “bursts“

But: this means the user has to read the documents!

Can we do better and create a concise summary of what was discussed in that period?

Can we allow the user to ask as much detail as s/he is interested in?

More advanced text modelling: Summarization – of time-indexed documents

28

Yes –

with

STORIES

(Subašić & Berendt,

Proc. ICDM 2008)

29

Salient story elements

1. Identify content-bearing terms (e.g. 150 top-TF.IDF over whole corpus)

2. Split whole corpus T by atomic time period (e.g., week)

3. For each time period (atomic or moving-average) Compute the weights for corpus t for this period Weight =

Support of co-occurrence of 2 content-bearing terms w1, w2 in t =

(# articles from t containing both w1, w2 in window) / (# all articles in t)

4. Threshold Number of occurrences of co-occurrence(w1, w2) in t ≥ θ1 (e.g., 5)

Time-relevance TR of co-occurrence(w1, w2) =

support(co-occurrence(w1, w2)) in t / support(co-occurrence(w1, w2)) in T ≥ θ2 (e.g., 2)

Thresholds are set dynamically + interactively by the user

5. Story elements = relationships = all these edges

Story basics = terms = all nodes connected by these edges

30

Salient story stages, and story evolution

6. Story stage = the story graph made of basics and elements in t

7. Story evolution = how story stages evolve over the t in T

31

An event: a missing child

32

A central figure emerges in the police investigations

33

Uncovering more details

34

Uncovering more details

35

An eventless time

36

The story and the underlying documents

37

(Berendt & Trümper, in press)

Navigating between documents; relating different source types to one another

38A simple form of opinion mining:Feature-based Summary (Hu and Liu, Proc. SIGKDD’04)

GREAT Camera., Jun 3, 2004

Reviewer: jprice174 from Atlanta, Ga.

I did a lot of research last year before I bought this camera... It kinda hurt to leave behind my beloved nikon 35mm SLR, but I was going to Italy, and I needed something smaller, and digital.

The pictures coming out of this camera are amazing. The 'auto' feature takes great pictures most of the time. And with digital, you're not wasting film if the picture doesn't come out. …….

Feature1: picture

Positive: 12

The pictures coming out of this camera are amazing.

Overall this is a good camera with a really good picture clarity.

…

Negative: 2

The pictures come out hazy if your hands shake even for a moment during the entire process of taking a picture.

Focusing on a display rack about 20 feet away in a brightly lit room during day time, pictures produced by this camera were blurry and in a shade of orange.

Feature2: battery life

…

Source: Product reviews similar to blogs, but (more) clearly product-related

39

Agenda

Concepts






So ...

40

An application: Crisis PR – Step 1:Use blogs to observe public discussions

Detect products about which there is controversial discussion

sentiment mining from text

and/or

use the structure of blogs (e.g., structure of blog post + comments; Mishne & Glance, Proc. WWW 2006)

and/or

discussion in the mainstream media (may be later though)

41

An application: Crisis PR – Step 2: Use blogs to communicate facts + own concerns

Example Dell‘s “exploding laptops“ – product recall and aftermath

Dell launched a blog at that time (much maligned at first, but they learned ...)

Evaluation of „all English-language consumer commentary on the Web“ before and after (methodology based on Reichhold 1996, The Loyalty Effect):

Market sentinel, 2007

42

Agenda

Concepts






So ...

43

First ...

... the imperfect nature of automatic text analysis presents a challenge

But: human inter-rater agreement on various aspects of texts also tends to be rather low!

44

Some findings

Only a fraction of the population blog (8% of adult Internet users - Pew Internet & American Life Project July 2006)

Most blogs are personal

US survey (Business Week July 2006)

German-language blogosphere is less “mature“, esp. Less politicized, than the US blogosphere (Berendt, Schlegel & Koch, 2008)

This includes fewer mentions of companies

But what about those personal blogs ...?

45

What makes people happy?

46

Happiness in blogosphere

47

Well kids, I had an awesome birthday thanks to you. =D Just wanted to so thank you for coming and thanks for the gifts and junk. =) I have many pictures and I will post them later. hearts

Well kids, I had an awesome birthday thanks to you. =D Just wanted to so thank you for coming and thanks for the gifts and junk. =) I have many pictures and I will post them later. hearts

current mood:

Home alone for too many hours, all week long ... screaming child, headache, tears that just won’t let themselves loose.... and now I’ve lost my wedding band. I hate this.

Home alone for too many hours, all week long ... screaming child, headache, tears that just won’t let themselves loose.... and now I’ve lost my wedding band. I hate this.

current mood:

What are the characteristic words of these two moods?

[Mihalcea, R. & Liu, H. (2006). In Proc. AAAI Spring Symposium CAAW.]

Slides based on Rada Mihalcea‘s presentation.

48

Data, data preparation and learning

LiveJournal.com – optional mood annotation

10,000 blogs:

5,000 happyhappy entries / 5,000 sadsad entries

average size 175 words / entry

post-processing – remove SGML tags, tokenization, part-of-speech tagging

quality of automatic “mood separation”

naïve bayes text classifier five-fold cross validation

Accuracy: 79.13% (>> 50% baseline)

49

Results: Corpus-derived happiness factors

yay 86.67

shopping 79.56

awesome 79.71

birthday 78.37

lovely 77.39

concert 74.85

cool 73.72

cute 73.20

lunch 73.02

books 73.02

goodbye 18.81hurt 17.39tears 14.35cried 11.39upset 11.12sad 11.11cry 10.56died 10.07lonely 9.50crying 5.50

happiness factor of a word = the number of occurrences in the happy blogposts / the total frequency in the corpus

50

Agenda

Concepts






So ...

51

Conclusion

[A brief glance given:] (Semi-)automated forms of text analysis, applied to blogs, can produce useful insights

[Only briefly mentioned today:] It can profit from the simultaneous analysis of link structures and/or tags

It is the only way of analysing large-scale corpora; mining methods are improving continuously

However, machine language understanding is not human language understanding

Also, representativeness is questionable

Need to combine blog mining with other forms of market research!

NB: These forms include Web usage mining, query mining, ...

But mining remains exploratory analysis

52

53

Literature and other sources

URLs of pictures are given in the “Comments“ of the slides.

Literature (Please note: Most of our papers are available at http://www.cs.kuleuven.be/~berendt):

pp. 22, 28-36: Subašić, I. & Berendt, B. (2008). Web mining for understanding stories through graph visualisation. In Proc. of the 2008 Eighth IEEE International Conference on Data Mining (pp. 570–579). Los Alamitos, CA: IEEE Computer Society Press.

pp. 23, 44: Berendt, B., Schlegel, M., & Koch, R. (2008). Die deutschsprachige Blogosphäre: Reifegrad, Politisierung, Themen und Bezug zu Nachrichtenmedien. In A. Zerfaß, M. Welker, & J. Schmidt (Eds.), Kommunikation, Partizipation und Wirkungen im Social Web (Band 2:Strategien und Anwendungen: Perspektiven für Wirtschaft, Politik, Publizistik) (pp. 72–96). Köln, Germany: Herbert von Halem Verlag.

pp. 25f: R. Feldman, M. Fresko, J. Goldenberg, O. Netzer, and L. H. Ungar (2007). Extracting product comparisons from discussion boards. In Proc. ICDM 2007, pp. 469–474. IEEE Computer Society, 2007. http://ieeexplore.ieee.org/iel5/4470209/4470210/04470275.pdf?arnumber=4470275

p. 37: Berendt, B. & Trümper, D. (in press). Semantics-based analysis and navigation of heterogeneous text corpora: the porpoise news and blogs engine. In I.-H. Ting (Ed.), Web Mining Applications in E-commerce and E-services, Berlin etc.: Springer.

p. 38: Minqing Hu and Bing Liu (2004). Mining and summarizing customer reviews. In Proc. SIGKDD’04 (pp. 168-177). http://portal.acm.org/citation.cfm?doid=1014052.1014073

p. 40: Gilad Mishne and Natalie Glance (2006). Leave a Reply: An Analysis of Weblog Comments. In Proc. WWE 2006. http://www.blogpulse.com/www2006-workshop/papers/wwe2006-discovery-lin-final.pdf

p. 41: market sentinel (2007). Responding to crisis using social media Updating the “Dell Hell” case study - are Dell turning opinion round? http://www.marketsentinel.com/files/Crisisresponseusingsocialmedia.pdf

p. 44: BusinessWeek - Jul 19 2006. A Survey: Majority of blogs are personal. (not online any more)

pp. 47-49: Mihalcea, R. & Liu, H. (2006). A corpus-based approach to finding happiness, In Proc. AAAI Spring Symposium on Computational Approaches to Analyzing Weblogs. http://www.cs.unt.edu/%7Erada/papers/mihalcea.aaaiss06.pdf

See http://wiki.esi.ac.uk/Current_Approaches_to_Data_Mining_Blogs for more articles on the subject.

1 Blog Mining – Market Research made easy? Bettina Berendt, K.U.Leuven, .

Documents

steps text mining

steps of text mining

idea of text mining

marketing slide

usenet slide

text preprocessing

blog mining market research

older media blogs