TFIDF-FL: Localizing Faults Using Term Frequency-Inverse Document Frequency and Deep Learning

Abstract

Existing fault localization based on neural networks utilize the information of whether a statement is executed or not executed to identify suspicious statements potentially responsible for a failure. However, the information just shows the binary execution states of a statement, and cannot show how important a statement is in executions. Consequently, it may degrade fault localization effectiveness. To address this issue, this paper proposes TFIDF-FL by using term frequency-inverse document frequency to identify a high or low degree of the influence of a statement in an execution. Our empirical results on 8 real-world programs show that TFIDF-FL significantly improves fault localization effectiveness.

A semantic similarity analysis of multiple English translations of The Analects: Based on a natural language processing algorithm

“…The algorithm is easily affected by the skew of the data set, such as a large number of documents in a certain category, which leads to the underestimation of IDF. IDF improvement algorithms such as TFIDF-FL ( Zhang et al, 2019 ) have been proposed, and some scholars have also suggested combining TF-IDF with Word2Vec to solve the shortcomings of TF-IDF ( Naeem et al, 2022 ); in short, simply using the TF-IDF algorithm to calculate semantic similarity leads to the problem of low accuracy.…”

“…The algorithm is easily affected by the skew of the data set, such as a large number of documents in a certain category, which leads to the underestimation of IDF. IDF improvement algorithms such as TFIDF-FL (Zhang et al, 2019) have been proposed, and some scholars have also suggested combining TF-IDF with Word2Vec to solve the shortcomings of TF-IDF (Naeem et al, 2022); in short, While the features of the SimHash algorithm are as mentioned above, its text similarity calculation is suitable for low-precision and high-speed scenarios. This calculation has lower requirements for speed but higher requirements for accuracy, which proves that SimHash is unsuitable for studying long texts or for high-precision similarity calculations.…”

Topic Detection on Twitter using GloVe with Convolutional Neural Network and Gated Recurrent Unit

“…TF-IDF computes the weight or value of each word (token) in a corpus document. This method is frequently utilized in information retrieval and text creation to evaluate the relationship of each word in a relationship document [21]. This normalization process determines the weight of terms that appear frequently in a document.…”