Document clustering: Difference between revisions

Revision as of 19:02, 18 March 2015

Latest revision as of 02:19, 10 January 2025

(45 intermediate revisions by 26 users not shown)

Line 1:

{{Short description|Grouping texts by similarity}}

{{Multiple issues|

{{disputed|date=March 2014}}

{{inlinemore footnotes needed|date=March 2014}}

}}

'''Document clustering''' (or '''text clustering''') is the application of [[cluster analysis]] to textual documents. It has applications in automatic document organization, [[topic (linguistics)|topic]] extraction and fast [[information retrieval]] or filtering.

Line 6 ⟶ 10:

Document clustering involves the use of descriptors and descriptor extraction. Descriptors are sets of words that describe the contents within the cluster. Document clustering is generally considered to be a centralized process. Examples of document clustering include web document clustering for search users.

The application of document clustering can be categorized to two types, online and offline. Online applications are usually constrained by efficiency problems when compared to offline applications. Text clustering may be used for different tasks, such as grouping similar documents (news, tweets, etc.) and the analysis of customer/employee feedback, discovering meaningful implicit subjects across all documents.

In general, there are two common algorithms. The first one is the hierarchical based algorithm, which includes single link, complete linkage, group average and Ward's method. By aggregating or dividing, documents can be clustered into hierarchical structure, which is suitable for browsing. However, such an algorithm usually suffers from efficiency problems. The other algorithm is developed using the [[K-means algorithm]] and its variants. TheseGenerally hierarchical algorithms canproduce furthermore bein-depth classifiedinformation asfor harddetailed oranalyses, soft clusteringwhile algorithms. Hardbased clusteringaround computes a hard assignment – each document is a membervariants of exactlythe one[[K-means cluster.algorithm]] Theare assignmentmore ofefficient softand clusteringprovide algorithmssufficient isinformation softfor –most a document’s assignment is a distribution over all clusterspurposes.<ref Inname="manning">Manning, a soft assignmentChris, aand documentHinrich has fractional membership in several clusters. [[Dimensionality reduction]] methods can be considered aSchütze, subtype''Foundations of softStatistical clustering;Natural forLanguage documentsProcessing'', theseMIT includePress. [[latentCambridge, semanticMA: indexing]]May ([[truncated singular value decomposition]] on term histograms)<ref>http://nlp1999.stanford.edu/IR-book/pdf/16flat.pdf</ref> and [[topic model]]s{{rp|Ch.14}}

These algorithms can further be classified as hard or soft clustering algorithms. Hard clustering computes a hard assignment – each document is a member of exactly one cluster. The assignment of soft clustering algorithms is soft – a document's assignment is a distribution over all clusters. In a soft assignment, a document has fractional membership in several clusters.<ref name="manning"/>{{rp|499}} [[Dimensionality reduction]] methods can be considered a subtype of soft clustering; for documents, these include [[latent semantic indexing]] ([[truncated singular value decomposition]] on term histograms)<ref>http://nlp.stanford.edu/IR-book/pdf/16flat.pdf {{Bare URL PDF|date=March 2022}}</ref> and [[topic model]]s.

Other algorithms involve graph based clustering, ontology supported clustering and order sensitive clustering.

Other algorithms involve graph based clustering, [[ontology (information science)|ontology]] supported clustering and order sensitive clustering.

Given a clustering, it can be beneficial to automatically derive human-readable labels for the clusters. [[Cluster labeling|Various methods]] exist for this purpose.

==Clustering in search engines==

A [[web search engine]] often returns thousands of pages in response to a broad query, making it difficult for users to browse or to identify relevant information. Clustering methods can be used to automatically group the retrieved documents into a list of meaningful categories, as is achieved by Enterprise Search engines such as [[Northern Light Group|Northern Light]] and [[Vivisimo]], consumer search engines such as [http://www.polymeta.com/ PolyMeta] and [http://www.helioid.com Helioid], or open source software such as [[Carrot2]].

==Procedures==

Examples:

In practice, document clustering often takes the following steps:

1. [[Tokenization (lexical analysis)|Tokenization]]

Tokenization is the process of parsing text data into smaller units (tokens) such as words and phrases. Commonly used tokenization methods include [[Bag-of-words model]] and [[N-gram model]].

* Clustering divides the results of a search for "cell" into groups like "biology," "battery," and "prison."

2. [[Stemming]] and [[lemmatization]]

* [http://FirstGov.gov FirstGov.gov], the official Web portal for the U.S. government, uses document clustering to automatically organize its search results into categories. For example, if a user submits “immigration”, next to their list of results they will see categories for “Immigration Reform”, “Citizenship and Immigration Services”, “Employment”, “Department of Homeland Security”, and more.

Different tokens might carry out similar information (e.g. tokenization and tokenizing). And we can avoid calculating similar information repeatedly by reducing all tokens to its base form using various stemming and lemmatization dictionaries.

3. Removing [[stop words]] and [[punctuation]]

Some tokens are less important than others. For instance, common words such as "the" might not be very helpful for revealing the essential characteristics of a text. So usually it is a good idea to eliminate stop words and punctuation marks before doing further analysis.

4. Computing term frequencies or [[tf-idf]]

After pre-processing the text data, we can then proceed to generate features. For document clustering, one of the most common ways to generate features for a document is to calculate the term frequencies of all its tokens. Although not perfect, these frequencies can usually provide some clues about the topic of the document. And sometimes it is also useful to weight the term frequencies by the inverse document frequencies. See [[tf-idf]] for detailed discussions.

5. Clustering

We can then cluster different documents based on the features we have generated. See the algorithm section in [[cluster analysis]] for different types of clustering methods.

6. Evaluation and visualization

Finally, the clustering models can be assessed by various metrics. And it is sometimes helpful to visualize the results by plotting the clusters into low (two) dimensional space. See [[multidimensional scaling]] as a possible approach.

== Clustering v. Classifying ==

Clustering algorithms in computational text analysis groups documents into grouping a set of text what are called subsets or ''clusters'' where the algorithm's goal is to create internally coherent clusters that are distinct from one another.<ref>{{Cite web|url=http://nlp.stanford.edu/IR-book/|title=Introduction to Information Retrieval|website=nlp.stanford.edu|pages=349|access-date=2016-05-03}}</ref> Classification on the other hand, is a form of [[supervised learning]] where the features of the documents are used to predict the "type" of documents.

==See Alsoalso==

*[[Cluster (disambiguation)|Cluster]]

*[[Fuzzy clustering]]

== References ==

{{reflist}}

Publications:

== Bibliography ==

* Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. ''Flat Clustering'' in <u>Introduction to Information Retrieval.</u> Cambridge University Press. 2008

* Nicholas O. Andrews and Edward A. Fox, Recent Developments in Document Clustering, October 16, 2007 [http://eprints.cs.vt.edu/archive/00001000/01/docclust.pdf]

* Claudio Carpineto, Stanislaw Osiński, Giovanni Romano, Dawid Weiss. A survey of Web clustering engines. ACM Computing Surveys (CSUR), Volume 41, Issue 3 (July 2009), Article No. 17, {{ISSN:|0360-0300 }}

*Wui Lee Chang, Kai Meng Tay, and Chee Peng Lim, A New Evolving Tree-Based Model with Local Re-learning for Document Clustering and Visualization, Neural Processing Letters, DOI: 10.1007/s11063-017-9597-3. https://link.springer.com/article/10.1007/s11063-017-9597-3

* http://semanticsearchart.com/researchBest.html - comparison of several popular clustering algorithms, data and software to reproduce the result.

* Tanmay Basu, C.A. Murthy , CUES: A New Hierarchical Approach for Document Clustering, 2013 [http://jprr.org JPRR]

{{Natural language processing}}

==See Also==

*[[Cluster Analysis]]

[[Category:Information retrieval techniques]]

*[[Fuzzy clustering]]

[[Category:Information retrieval]]