Subjective Evaluation: A Comparison of Several Statistical Techniques

Mittal, Himani; Devi, M. Syamala

doi:10.1080/08839514.2018.1451095

Cited by 8 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, finding similar words based on their frequent collocation. The following algorithms and methods are considered as text corpus semantic similarity www.aetic.theiaer.org algorithms: Hyperspace Analogue to Language (HAL) [33], Latent Semantic Analysis (LSA) [34], Generalized Latent Semantic Analysis (GLSA) [35], Explicit Semantic Analysis (ESA) [36], Pointwise Mutual Information -Information Retrieval (PMI-IR) [37], Second-order co-occurrence point wise mutual information (SCO-PMI) [38], Normalized Google Distance (NGD) [39] and Extracting DIStributionally similar words using COoccurrences (DISCO) [40]. For these algorithms to work accurately and effectively, a vast and clean textual corpus must be used, and they deduce similarity based on textual collocations.…”

Section: Related Workmentioning

confidence: 99%

Similarity Detection of Time-Sensitive Online News Articles Based on RSS Feeds and Contextual Data

Daoud¹

2023

AETiC

View full text Add to dashboard Cite

This article tackles the problem of finding similarity between web time-sensitive news articles, which can be a challenge. This challenge was approached with a novel methodology that uses supervised learning algorithms with carefully selected features (Semantic, Lexical and Temporal features (content and contextual features)). The proposed approach considers not only the textual content, which is a well-studied approach that may yield misleading results, but also the context, community engagement, and community-deduced importance of that news article. This paper details the major procedures of title pair pre-processing, analysis of lexical units, feature engineering, and similarity measures. Thousands of web articles are being published every second, and therefore, it is essential to determine the similarity of these articles efficiently without wasting time on unnecessary text processing of the bodies. Hence, the proposed approach focuses on short contents (titles) and context. The conducted experiment showed high precision and accuracy on a Really Simple Syndication (RSS) dataset of 8000 Arabic news article pairs collected automatically from 10 different news sources. The proposed approach achieved an accuracy of 0.81. Contextual features increased the accuracy and the precision. The proposed algorithm achieved a 0.89 correlation with the evaluations of two human judges based on Pearson’s Correlation Coefficient. The results outperform the state-of-the-art systems on Arabic news articles.

show abstract

Section: Related Workmentioning

confidence: 99%

Similarity Detection of Time-Sensitive Online News Articles Based on RSS Feeds and Contextual Data

Daoud¹

2023

AETiC

View full text Add to dashboard Cite

show abstract

“…Evaluation interest of consider and exactness come to be used, and as a quit result, the contraption's common overall to be 50.9% with and 48.7% without the opportunity of revel being made. Xia et al [8] mixed the word2vec structure with the undermining report corpus to see the worth in similarities among stand-separated rule records. As a quit outcome, word2vec managed the accuracy with the asset of the use of 0.2 in evaluation to the sack of terms structure, that might in basically a near way whenever at some point at long last be associated with the asset of the utilization of 0.05-0.10 through setting up the word2vec model on rule stories.…”

Section: Literature Surveymentioning

confidence: 99%

Evaluating Descriptive Answer Using Machine Learning And Natural Language Processing

Kumari¹,

Kumar²,

Ahmed³

et al. 2022

EJASR

View full text Add to dashboard Cite

Assessment of the descriptive paper is a tough challenge. It requires lot of man power. In educational institutions a primary hassle is evaluation of descriptive type questions & answers. Using NLP this descriptive answer assessment proper answers and the pupil answer scripts. More marks is probably awarded, if the similarity withinside the answers is more. There are several advantages of using this automated assessment device as it permits in decreasing the time concerned about the resource of the usage of faculty to correct the descriptive papers. The examinations can be accomplished online, the answers can be evaluated right now and it would be beneficial for universities, schools and schools for academic purpose with the resource of the usage of presenting ease to colleges and the examination evaluation cell.

show abstract

“…It is based on keyword matching and is considered poor as it cannot tackle problems such as synonyms or take the context into account. Several works have been done on subjective paper evaluation using this approach [9] [10].…”

Section: ) Statistical Techniquementioning

confidence: 99%

Subjective Answers Evaluation Using Machine Learning and Natural Language Processing

Bashir

Arshad

Javed³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Subjective paper evaluation is a tricky and tiresome task to do by manual labor. Insufficient understanding and acceptance of data are crucial challenges while analyzing subjective papers using Artificial Intelligence (AI). Several attempts have been made to score students' answers using computer science. However, most of the work uses traditional counts or specific words to achieve this task. Furthermore, there is a lack of curated data sets as well. This paper proposes a novel approach that utilizes various machine learning, natural language processing techniques, and tools such as Wordnet, Word2vec, word mover's distance (WMD), cosine similarity, multinomial naive bayes (MNB), and term frequencyinverse document frequency (TF-IDF) to evaluate descriptive answers automatically. Solution statements and keywords are used to evaluate answers, and a machine learning model is trained to predict the grades of answers. Results show that WMD performs better than cosine similarity overall. With enough training, the machine learning model could be used as a standalone as well. Experimentation produces an accuracy of 88% without the MNB model. The error rate is further reduced by 1.3% using MNB.

show abstract

Subjective Evaluation: A Comparison of Several Statistical Techniques

Cited by 8 publications

References 5 publications

Similarity Detection of Time-Sensitive Online News Articles Based on RSS Feeds and Contextual Data

Similarity Detection of Time-Sensitive Online News Articles Based on RSS Feeds and Contextual Data

Evaluating Descriptive Answer Using Machine Learning And Natural Language Processing

Subjective Answers Evaluation Using Machine Learning and Natural Language Processing

Contact Info

Product

Resources

About