Automatic multilabel categorization using learning to rank framework for complaint text on Bandung government

Fauzan, Ahmad; Khodra, Masayu Leylia

doi:10.1109/icaicta.2014.7005910

Cited by 10 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…LTR was proposed in the context of ad hoc information retrieval in which the goal is to create a ranking model that ranks documents with respect to queries . The LTR approach has been used for constructing a ranking model to rank classes with respect to a given document and select the most probable classes for the document as its labels (Yang and Gopal 2012; Ju, Moschitti, and Johansson 2013; Fauzan and Khodra 2014; Azarbonyad and Marx 2019). Yang and Gopal (2012) mapped MLTC to the ad hoc retrieval problem and used LTR for learning a ranking model.…”

Section: Related Workmentioning

confidence: 99%

“…While this method has been shown to have a good performance in MLTC, it does not take the relations between classes into account in the MLTC task. Fauzan and Khodra (2014) used the same framework for classifying documents; however, they focused on text classification, and instead of using meta-level features, they used typical features such as TF-IDF weights of words for learning an LTR model. Their method also outperforms traditional classification-based approaches.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning to rank for multi-label text classification: Combining different sources of information

et al. 2020

View full text Add to dashboard Cite

Efficiently exploiting all sources of information such as labeled instances, classes' representation, and relations of them has a high impact on the performance of Multi-Label Text Classification (MLTC) systems. Most of the current approaches use labeled documents as the primary source of information for MLTC. We investigate the effectiveness of different sources of information-such as the labeled training data, textual labels of classes, and taxonomy relations of classes-for MLTC. More specifically, first, for each document-class pair, different features are extracted using different sources of information. The features reflect the similarity of classes and documents. Then, MLTC is considered to be a ranking problem, and a learning to rank (LTR) approach is used for ranking classes regarding documents and selecting labels of documents. An important characteristic of many MLTC instances is that documents can belong to multiple classes and there are implicit relations between classes. We apply score propagation on top of LTR to incorporate co-occurrence patterns of classes in labeled documents. Our main findings are the following. First, using an LTR approach integrating all features, we observe significantly better performance than previous systems for MLTC. Specifically, we show that simple classification approaches fail when there is a high number of classes. Second, the analysis of feature weights reveals the relative importance of various sources of evidence, also giving insight into the underlying classification problem. Interestingly, the results indicate that the titles of documents are more informative than all other sources of information. Third, a lean-and-mean system using only four features is able to perform at 96% of the large LTR model that we propose in this paper. Fourth, using the co-occurrence information of classes helps in classifying documents more accurately. Our results show that the co-occurrence information is more helpful when the underlying classifier has a poor performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Learning to rank for multi-label text classification: Combining different sources of information

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To our knowledge, there are only 2 previous researches [6], [7] which focus on handling imbalanced dataset for multi-label text categorization. This paper uses LAPOR dataset which was used before in previous research [8], but [8] did not handle the issue. On the other hand, we consider the dataset is too small to generalize all possible occurrences because [8] only has 2230 data.…”

Section: Introductionmentioning

confidence: 99%

“…This paper uses LAPOR dataset which was used before in previous research [8], but [8] did not handle the issue. On the other hand, we consider the dataset is too small to generalize all possible occurrences because [8] only has 2230 data. Thus, we acquired 2921 more instances from the institution who collects those data.…”

Section: Introductionmentioning

confidence: 99%

Handling imbalanced dataset in multi-label text categorization using Bagging and Adaptive Boosting

Winata

Khodra

2015

2015 International Conference on Electrical Engineering and Informatics (ICEEI)

Self Cite

View full text Add to dashboard Cite

Imbalanced dataset is occurred due to uneven distribution of data available in the real world such as disposition of complaints on government offices in Bandung. Consequently, multi-label text categorization algorithms may not produce the best performance because classifiers tend to be weighed down by the majority of the data and ignore the minority. In this paper, Bagging and Adaptive Boosting algorithms are employed to handle the issue and improve the performance of text categorization. The result is evaluated with four evaluation metrics such as hamming loss, subset accuracy, example-based accuracy and micro-averaged f-measure. Bagging.ML-LP with SMO weak classifier is the best performer in terms of subset accuracy and example-based accuracy. Bagging.ML-BR with SMO weak classifier has the best micro-averaged f-measure among all. In other hand, AdaBoost.MH with J48 weak classifier has the lowest hamming loss value. Thus, both algorithms have high potential in boosting the performance of text categorization, but only for certain weak classifiers. However, bagging has more potential than adaptive boosting in increasing the accuracy of minority labels.

show abstract

“…Administrator yang terbatas dan angka laporan pengaduan yang cukup tinggi menjadi penyebab utama kurangnya kualitas layanan terutama karakteristik daya tanggap (responsivitas) [2]. Penanganan laporan bergantung pada administrator sistem yang membaca secara manual setiap laporan yang masuk [3]. Hal ini dapat menyebabkan kesalahan dalam menangani keluhan [4], dan jika aliran datanya sangat besar dapat membutuhkan waktu minimal tiga hari, hal ini sensitif terhadap inkonsistensi [3].…”

unclassified

Identifikasi Kemiripan Teks Menggunakan Class Indexing Based dan Cosine Similarity Untuk Klasifikasi Dokumen Pengaduan

Iriananda

Muslim

Dachlan

2019

View full text Add to dashboard Cite

Report handling on "LAPOR!" systemdepends on the system administrator who manually reads every incoming report [3]. Read manually can lead to errors in handling complaints [4] if the data flow is very large and grows rapidly it can take at least three days and sensitive to inconsistencies [3]. In this study, the authors propose a model that can measure and identify the similarity of document reports computerized that can identify the similarity between the Query (Incoming) with Document (Archive). In this study, the authors employed term weighting scheme Class-Based Indexing, and Cosine Similarity to analyze document similarities. CoSimTFIDF, CoSimTFICF and CoSimTFIDFICF values are defined as feature sets for the text classification process using the KNearest Neighbor (K-NN) method. The optimum result evaluation with preprocessing employ Stemming and the best result of all features is 75% training data ratio and 25% test data on the CoSimTFIDF feature that is 84%. Value k = 5 has a high accuracy of 84.12%

show abstract

Automatic multilabel categorization using learning to rank framework for complaint text on Bandung government

Cited by 10 publications

References 23 publications

Learning to rank for multi-label text classification: Combining different sources of information

Learning to rank for multi-label text classification: Combining different sources of information

Handling imbalanced dataset in multi-label text categorization using Bagging and Adaptive Boosting

Identifikasi Kemiripan Teks Menggunakan Class Indexing Based dan Cosine Similarity Untuk Klasifikasi Dokumen Pengaduan

Contact Info

Product

Resources

About