An implementation of clustering project proposals on ontology based text mining approach

Preethi, T.; Lakshmi, R. Deepa

doi:10.1109/icices.2013.6508288

Cited by 6 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a research ontology was constructed using the keywords associated with the research project. However, keywords alone are insufficient for identifying the correct research topic (Preethi and Lakshmi, 2013). Keywords and discipline areas do not contain all the information needed to assess project proposals.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In some studies, proposals are grouped based on the keywords declared by the project applicants. Regrettably, in this case, proposals with similar research areas may be incorrectly grouped, given that keywords are imprecise descriptions of the proposals' full content; they may reflect subjective views and misconceptions since the applicants provide them and represent only a portion of the research proposal's text (Hettich and Pazzani, 2006; Ma et al ., 2012; Preethi and Lakshmi, 2013; Arunachala et al ., 2013; Patil and Uddin, 2015). Therefore, using the rich information in the project proposals eliminates the disadvantages of current methods and provides more accurate results (Safi'ie et al ., 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

“…In response to the need for automatic grouping of proposals, ontology-based text mining (OTMM) technology has frequently been used to automatically group project proposals (Ma et al ., 2012; Rathore et al ., 2013; Preethi and Lakshmi, 2013; Patil and Uddin, 2015; Xu et al ., 2013; Rajkamal, 2017). An ontology is a systematic description of a concept and its associated properties within a domain.…”

Section: Literature Reviewmentioning

confidence: 99%

“…After developing a research ontology or performing feature extraction, documents are grouped according to their similarities. Various clustering techniques have been used for this purpose, such as the self-organizing map (SOM) (Wang et al ., 2015; Saravanan and Babu, 2017; Ma et al ., 2012; Ahmed et al ., 2020), expectation-maximization (Wang et al ., 2015; Rajkamal, 2017), k-means (Xu et al ., 2013; Patil and Uddin, 2015; Rajkamal, 2017), DBSCAN (Rajkamal, 2017) fuzzy c-means (Preethi and Lakshmi, 2013; Kumar et al ., 2019). Document classification methods include k-nearest neighbor (KNN) (Rathore et al ., 2013; Safi'ie et al ., 2018; Chowdhury and Schoen, 2020), naive bayes (Rathore et al ., 2013; Saravanan and Babu, 2017) and support vector machines (SVM) Saravanan and Babu (2017), Dominic and R (2021) and C4.5 (Rajkamal, 2017) are presented.…”

Section: Literature Reviewmentioning

confidence: 99%

See 3 more Smart Citations

A comparative analysis of text representation, classification and clustering methods over real project proposals

Aksoy

Yanık

Amasyalı

2023

IJICC

View full text Add to dashboard Cite

PurposeWhen a large number of project proposals are evaluated to allocate available funds, grouping them based on their similarities is beneficial. Current approaches to group proposals are primarily based on manual matching of similar topics, discipline areas and keywords declared by project applicants. When the number of proposals increases, this task becomes complex and requires excessive time. This paper aims to demonstrate how to effectively use the rich information in the titles and abstracts of Turkish project proposals to group them automatically.Design/methodology/approachThis study proposes a model that effectively groups Turkish project proposals by combining word embedding, clustering and classification techniques. The proposed model uses FastText, BERT and term frequency/inverse document frequency (TF/IDF) word-embedding techniques to extract terms from the titles and abstracts of project proposals in Turkish. The extracted terms were grouped using both the clustering and classification techniques. Natural groups contained within the corpus were discovered using k-means, k-means++, k-medoids and agglomerative clustering algorithms. Additionally, this study employs classification approaches to predict the target class for each document in the corpus. To classify project proposals, various classifiers, including k-nearest neighbors (KNN), support vector machines (SVM), artificial neural networks (ANN), classification and regression trees (CART) and random forest (RF), are used. Empirical experiments were conducted to validate the effectiveness of the proposed method by using real data from the Istanbul Development Agency.FindingsThe results show that the generated word embeddings can effectively represent proposal texts as vectors, and can be used as inputs for clustering or classification algorithms. Using clustering algorithms, the document corpus is divided into five groups. In addition, the results demonstrate that the proposals can easily be categorized into predefined categories using classification algorithms. SVM-Linear achieved the highest prediction accuracy (89.2%) with the FastText word embedding method. A comparison of manual grouping with automatic classification and clustering results revealed that both classification and clustering techniques have a high success rate.Research limitations/implicationsThe proposed model automatically benefits from the rich information in project proposals and significantly reduces numerous time-consuming tasks that managers must perform manually. Thus, it eliminates the drawbacks of the current manual methods and yields significantly more accurate results. In the future, additional experiments should be conducted to validate the proposed method using data from other funding organizations.Originality/valueThis study presents the application of word embedding methods to effectively use the rich information in the titles and abstracts of Turkish project proposals. Existing research studies focus on the automatic grouping of proposals; traditional frequency-based word embedding methods are used for feature extraction methods to represent project proposals. Unlike previous research, this study employs two outperforming neural network-based textual feature extraction techniques to obtain terms representing the proposals: BERT as a contextual word embedding method and FastText as a static word embedding method. Moreover, to the best of our knowledge, there has been no research conducted on the grouping of project proposals in Turkish.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

A comparative analysis of text representation, classification and clustering methods over real project proposals

Aksoy

Yanık

Amasyalı

2023

IJICC

View full text Add to dashboard Cite

show abstract

“…The scientific department, the DM unit responsible for subsidising proposals understood that the decision process fails to be accurate. Later, a novel ontology-based text mining method was proposed to bunch proposals and overcome the inaccuracy issue (Preethi & Lakshmi, 2013).…”

Section: Predictive Analytics With Digital Technologies For Dmmentioning

confidence: 99%

A Systematic review of ontology-based approach and decision-making (DM) to improve public service delivery (PSD)

Ali

Latiff

Wahab³

2020

JBSEE

View full text Add to dashboard Cite

A systematic review of the DM literature on PSD was performed with the aim to build an operational ontology-based for decision makers. Five public administration journals were screened on the subject with more than 200 articles found. 29 articles were shortlisted, categorised, summarised, and applied to outline the influential factors in DM for PSD. The result of the systematic reviews also provided a brief clarification on the requirement for the creation of a more citizen-centric and coordinated eco-system for efficient PSD underpinned by effective DM.

show abstract

Intelligent Word Embedding Methods to Support Project Proposal Grouping for Project Selection

Aksoy

Amasyalı

Yanık

2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

An implementation of clustering project proposals on ontology based text mining approach

Cited by 6 publications

References 10 publications

A comparative analysis of text representation, classification and clustering methods over real project proposals

A comparative analysis of text representation, classification and clustering methods over real project proposals

A Systematic review of ontology-based approach and decision-making (DM) to improve public service delivery (PSD)

Intelligent Word Embedding Methods to Support Project Proposal Grouping for Project Selection

Contact Info

Product

Resources

About