Latent Semantic Indexing Technique Research Articles

Pemanfaatan Latent Semantic Indexing untuk Mengukur Potensi Kerjasama Jurnal Ilmiah Lintas Universitas

Abstract— This paper presents a cooperation recommendation strategy between higher education institution. The recommendation is based on the contents of journals published in a university journal portal. As a case study, we concentrate our approach for the journals with information technology themes. All journals from 10 reputed universities will be compared by using keywords and the contents of the journal themselves. A partnering recommendation list is built by utilizing Latent Semantic Indexing (LSI). LSI technique is used to reduce the curse of dimensionality from the original data set and to generate topical analysis from all journals as semantic representation for each journals. Topic modeling is used to calculate the categorical similarity in the data set of each university journal and a search query. After all categorical similarities have been calculated, an average value of journal topics coherence is used to construct the final recommendation of partner candidates. This approach ensure that the final recommendation is based on the interest of each university rather than the frequencies of matched keywords in each journal.

Enhanced Latent Semantic Indexing Using Cosine Similarity Measures for Medical Application

The Vector Space Model (VSM) is widely used in data mining and Information Retrieval (IR) systems as a common document representation model. However, there are some challenges to this technique such as high dimensional space and semantic looseness of the representation. Consequently, the Latent Semantic Indexing (LSI) was suggested to reduce the feature dimensions and to generate semantic rich features that can represent conceptual term-document associations. In fact, LSI has been effectively employed in search engines and many other Natural Language Processing (NLP) applications. Researchers thereby promote endless effort seeking for better performance. In this paper, we propose an innovative method that can be used in search engines to find better matched contents of the retrieving documents. The proposed method introduces a new extension for the LSI technique based on the cosine similarity measures. The performance evaluation was carried out using an Arabic language data collection that contains 800 medical related documents, with more than 47,222 unique words. The proposed method was assessed using a small testing set that contains five medical keywords. The results show that the performance of the proposed method is superior when compared to the standard LSI

Vantage Point Latent Semantic Indexing for multimedia web document search

Latent Semantic Indexing (LSI) successfully retrieves the relations between the text documents. LSI technique achieves dynamic clustering on the basis of conceptual contents of documents. But, inaccurate extraction to essential sentences, retrieval time and redundancy poses significant challenges and has to be addressed. Also, the LSI technique does not address the problem of document search with multimedia contents. This paper introduces a new concept of vantage point called, Vantage Point Latency Semantic Indexing (VP-LSI) to improve the retrieving accuracy and fastness of clustered multimedia web document. Rayleigh cluster SOM web document are indexed with vantage point of predominant word in the clusters. Similarly, the vantage point for the multimedia objects are used to cluster the multimedia documents. Vantage point is calculated based on the relative strength of the predominant word to Rayleigh clusters in the domain area with mean and standard deviation. The Vantage point for the image objects are estimated based on the mean and standard deviation of histogram values. Then, indexing of the cluster objects are initialized to the documents. Finally, retrievals of web document based on user query are searched in the indexed Rayleigh cluster objects to fetch more accurate web document in quicker time. Experimental evaluation is conducted with searching of web document in multiple domain area available in research repositories. The results show that the proposed method results in lesser time than the existing algorithm. Moreover, the proposed method results in better search document accuracy, reducing the time to retrieve web documents and indexing rate than the existing Lexical Semantic Indexing approach.

Asymmetric latent semantic indexing for gene expression experiments visualization.

We propose a new method to visualize gene expression experiments inspired by the latent semantic indexing technique originally proposed in the textual analysis context. By using the correspondence word-gene document-experiment, we define an asymmetric similarity measure of association for genes that accounts for potential hierarchies in the data, the key to obtain meaningful gene mappings. We use the polar decomposition to obtain the sources of asymmetry of the similarity matrix, which are later combined with previous knowledge. Genetic classes of genes are identified by means of a mixture model applied in the genes latent space. We describe the steps of the procedure and we show its utility in the Human Cancer dataset.

FIR: An Effective Scheme for Extracting Useful Metadata from Social Media.

Recently, the use of social media for health information exchange is expanding among patients, physicians, and other health care professionals. In medical areas, social media allows non-experts to access, interpret, and generate medical information for their own care and the care of others. Researchers paid much attention on social media in medical educations, patient-pharmacist communications, adverse drug reactions detection, impacts of social media on medicine and healthcare, and so on. However, relatively few papers discuss how to extract useful knowledge from a huge amount of textual comments in social media effectively. Therefore, this study aims to propose a Fuzzy adaptive resonance theory network based Information Retrieval (FIR) scheme by combining Fuzzy adaptive resonance theory (ART) network, Latent Semantic Indexing (LSI), and association rules (AR) discovery to extract knowledge from social media. In our FIR scheme, Fuzzy ART network firstly has been employed to segment comments. Next, for each customer segment, we use LSI technique to retrieve important keywords. Then, in order to make the extracted keywords understandable, association rules mining is presented to organize these extracted keywords to build metadata. These extracted useful voices of customers will be transformed into design needs by using Quality Function Deployment (QFD) for further decision making. Unlike conventional information retrieval techniques which acquire too many keywords to get key points, our FIR scheme can extract understandable metadata from social media.

Framework for Document Retrieval using Latent Semantic Indexing

with the rapid development of the Internet, textual information is growing rapidly. So document retrieval which aims to find and organize relevant information in text collections is needed. With the availability of large scale inexpensive storage the amount of information stored by organizations will increase. Searching for information and deriving useful facts will become more cumbersome. How to extract a lot of information quickly and effectively has become the focus of current research and hot topics. The state of the art for traditional IR techniques is to find relevant documents depending on matching words in users' query with individual words in text collections. The problem with Content-based retrieval systems is that documents relevant to a users' query are not retrieved, and many unrelated or irrelevant materials are retrieved. In this paper information retrieval method is proposed based on LSI approach. Latent Semantic Indexing (LSI) model is a concept based retrieval method that exploits the idea of vector space model and singular value decomposition. The goal of this research is to evaluate the applicability of LSI technique for textual document search and retrieval.

Using Topic Analysis for Querying Halal Information on Malay Documents

Many documents with descriptions of halal products are available through resources from the Internet web pages. User may enquire for halal-related information through query words and as a result of the query user will be present- ed list of documents relevant to the query. We investigate on topic analysis techniques such as Latent Semantic Anal- ysis (LSA). For retrieval purposes, frequency-based inverted indexing and latent semantic indexing (LSI) techniques are used to discover the important association of the relationship between terms and terms, terms and documents and documents and documents. Cosine similarity measurement is used to measure the similarity between the query word and terms as well as the documents. We develop a prototype and evaluate the techniques on Malay test collection which contain documents extracted from translated Al-Quran collection, translated hadiths collection and web pages written in Malay language. Results and analysis show that, LSI technique outperformed the exact frequency-based technique despite the longer processing time it took during the indexing. We compare and discuss the result we get from using latent semantic with the result from using conventional frequency analysis.

Indian Languages IR using Latent Semantic Indexing

Retrieving information from different languages may lead to many problems like polysemy and synonymy, which can be resolved by Latent Semantic Indexing (LSI) techniques. This paper uses the Singular Value Decomposition (SVD) of LSI technique to achieve effective indexing for English and Hindi languages. Parallel corpus consisting of both Hindi and English documents is created and is used for training and testing the system. Removing stop words from the documents is performed followed by stemming and normalization in order to reduce the feature space and to get language relations. Then, cosine similarity method is applied on query document and target document. Based on our experimental results it is proved that LSI based CLIR gets over the non-LSI based retrieval which have retrieval successes of 67% and 9% respectively.

지도적 잠재의미색인(LSI)기법을 이용한 의견 문서 자동 분류에 관한 실험적 연구

본 연구에서는 의견이나 감정을 담고 있는 의견 문서들의 자동 분류 성능을 향상시키기 위하여 개념색인의 하나인 잠재의미색인 기법을 사용한 분류 실험을 수행하였다. 실험을 위해 수집한 1,000개의 의견 문서는 500개씩의 긍정 문서와 부정 문서를 포함한다. 의견 문서 텍스트의 형태소 분석을 통해 명사 형태의 내용어 집합과 용언, 부사, 어기로 구성되는 의견어 집합을 생성하였다. 각기 다른 자질 집합들을 대상으로 의견 문서를 분류한 결과 용어색인에서는 의견어 집합, 잠재의미색인에서는 내용어와 의견어를 통합한 집합, 지도적 잠재의미색인에서는 내용어 집합이 가장 좋은 성능을 보였다. 전체적으로 의견 문서의 자동 분류에서 용어색인 보다는 잠재의미색인 기법의 분류 성능이 더 좋았으며, 특히 지도적 잠재의미색인 기법을 사용할 경우 최고의 분류 성능을 보였다.

Concept based clustering for descriptive document classification

We present an approach for improving the relevance of search results by clustering the search results obtained for a query string with the help of a Concept Clustering Algorithm. The Concept Clustering Algorithm combines common phrase discovery and latent semantic indexing techniques to separate search results into meaningful groups. It looks for meaningful phrases to use as cluster labels and then assigns documents to the labels to form groups. The labels assigned to each document cluster provide meaningful information on the various documents available under that cluster. This provides a more interactive and easier way to probe through search results and identifying the relevant documents for the users using the search engine.

A Concept-Driven Algorithm for Clustering Search Results

Without search engines, the Internet would be an enormous amount of disorganized information that would certainly be interesting but perhaps not very useful. Search engines help us in all kinds of tasks and are constantly improving result relevance. The Lingo algorithm combines common phrase discovery and latent semantic indexing techniques to separate search results into meaningful groups. It looks for meaningful phrases to use as cluster labels and then assigns documents to the labels to form groups.