# Latent semantic analysis

둘러보기로 가기
검색하러 가기

## 노트

- To reduce complexity, the size of the semantic space was optimized by LSA to have n = 300 dimensions.
^{[1]} - LSA was used to compute a dissimilarity measure by computing the cosine between each pair of terms in the set to produce a distance matrix.
^{[1]} - In this paper, we use Latent Semantic Analysis (LSA) to help identify the emerging research trends in OSM.
^{[2]} - That is why latent semantic indexing (LSI) is extremely important for websites to adopt in 2018.
^{[3]} - Latent Semantic Indexing (LSI) has long been cause for debate amongst search marketers.
^{[4]} - Google the term ‘latent semantic indexing’ and you will encounter both advocates and sceptics in equal measure.
^{[4]} - However, LSA has a high computational cost for analyzing large amounts of information.
^{[5]} - Section 2 introduces the related background of LSA.
^{[5]} - Hence, LSA uses a normalized matrix which can be large and rather sparse.
^{[5]} - Thus, we have compared the execution time of the hLSA and LSA (CPU sequential-only) system.
^{[5]} - The adequacy of LSA's reflection of human knowledge has been established in a variety of ways.
^{[6]} - Of course, LSA, as currently practiced, induces its representations of the meaning of words and passages from analysis of text alone.
^{[6]} - However, LSA as currently practiced has some additional limitations.
^{[6]} - LSA differs from other statistical approaches in two significant respects.
^{[6]} - The first step in Latent Semantic Analysis is to create the word by title (or document) matrix.
^{[7]} - In general, the matrices built during LSA tend to be very large, but also very sparse (most cells contain 0).
^{[7]} - The LSA class has methods for initialization, parsing documents, building the matrix of word counts, and calculating.
^{[7]} - The first method is the __init__ method, which is called whenever an instance of the LSA class is created.
^{[7]} - LSA is one such technique that can find these hidden topics.
^{[8]} - It’s time to power up Python and understand how to implement LSA in a topic modeling problem.
^{[8]} - The LSA uses an input document-term matrix that describes the occurrence of group of terms in documents.
^{[9]} - In more practical terms: “Latent semantic analysis automatically extracts the concepts contained in text documents.
^{[10]} - LSA package for R developed by Fridolin Wild.
^{[10]} - When Using Latent Semantic Analysis For Evaluating Student Answers?
^{[10]} - LSA learns latent topics by performing a matrix decomposition on the document-term matrix using Singular value decomposition.
^{[11]} - Here, 7 Topics were discovered using Latent Semantic Analysis.
^{[11]} - LSA closely approximates many aspects of human language learning and understanding.
^{[12]} - This is the best (in a least squares sense) approximation to \(X\) with \(k\) parameters, and is what LSA uses for its semantic space.
^{[12]} - Free SVD and LSA packages include SVDPACK/SVDPACKC which use iterative methods to compute the SVD of large sparse matrices.
^{[12]} - LSA has been used most widely for small database IR and educational technology applications.
^{[12]} - The LSA returns concepts instead of topics which represents the given document.
^{[13]} - LSA assumes that words that are close in meaning will occur in similar pieces of text (the distributional hypothesis).
^{[14]} - For LSA, we generate a matrix by using the words present in the paragraphs of the document in the corpus.
^{[15]} - LSA could be leveraged to extract text summaries from text documents or even product descriptions (like the example above).
^{[15]} - LSA along with SVD can help with topic modelling on a text corpus.
^{[15]} - Make sure to read his excellent post on SEO by the Sea: Does Google Use Latent Semantic Indexing?
^{[16]} - LSA chose the most similar alternative word as that with the largest cos to the question word.
^{[17]} - In standard LSA, the solution of such a system is accomplished by SVD ( 3 ).
^{[17]} - LSA is one of a growing number of corpus-based techniques that employ statistical machine learning in text analysis.
^{[17]} - ( 5 ), and the string-edit-based method of S. Dennis ( 6 ) and several new computational realizations of LSA.
^{[17]} - LDA was introduced in 2003 by David Blei, Andrew Ng, and Michael I. Jordan and is also a type of unsupervised learning as LSA.
^{[18]} - Latent semantic analysis is centered around computing a partial singular value decomposition (SVD) of the document term matrix (DTM).
^{[19]} - Latent semantic analysis also captures indirect connections.
^{[19]} - so I started with Latent Semantic Analysis and used this tutorial to build the algorithm.
^{[20]}

### 소스

- ↑
^{1.0}^{1.1}Application of latent semantic analysis for open-ended responses in a large, epidemiologic study - ↑ Using Latent Semantic Analysis to Identify Research Trends in OpenStreetMap
- ↑ How to Use Latent Semantic Indexing Keywords to Boost Your SEO
- ↑
^{4.0}^{4.1}What is Latent Semantic Indexing? - ↑
^{5.0}^{5.1}^{5.2}^{5.3}A Heterogeneous System Based on Latent Semantic Analysis Using GPU and Multi-CPU - ↑
^{6.0}^{6.1}^{6.2}^{6.3}What is LSA? - ↑
^{7.0}^{7.1}^{7.2}^{7.3}Latent Semantic Analysis (LSA) Tutorial - ↑
^{8.0}^{8.1}Topic Modelling In Python Using Latent Semantic Analysis - ↑ Latent Semantic Analysis (LSA)
- ↑
^{10.0}^{10.1}^{10.2}Latent semantic analysis and indexing - ↑
^{11.0}^{11.1}Latent Semantic Analysis using Python - ↑
^{12.0}^{12.1}^{12.2}^{12.3}Latent semantic analysis - ↑ Latent Semantic Analysis — Deduce the hidden topic from the document
- ↑ Latent semantic analysis
- ↑
^{15.0}^{15.1}^{15.2}What is Latent Semantic Analysis (LSA)? - ↑ What Is Latent Semantic Indexing & Why It Won’t Help Your SEO
- ↑
^{17.0}^{17.1}^{17.2}^{17.3}From paragraph to graph: Latent semantic analysis for information visualization - ↑ Introduction of Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA)
- ↑
^{19.0}^{19.1}Latent Semantic Analysis (SVD) - ↑ nltk latent semantic analysis copies the first topics over and over

## 메타데이터

### 위키데이터

- ID : Q1806883