Multi-label dataless text classification with topic modeling

Zha, Daochen; Li, Chenliang

doi:10.1007/s10115-018-1280-0

Cited by 35 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section briefly discusses the preliminary study conducted to compile the domain knowledge related to PEN model traits [22]. The motivation to compile the seed words aggregated to personality models was raised due to the representation power of such terms in revealing the demographical of the topical categories [5]. In this sense, we adopted a mechanism called Automatic Personality Perceptions (APP) and executed a survey to gather public perception towards the list of the sentiment words extracted from myPersonality using Part-of-Speech Tagging elements.…”

Section: Overview Of the Preliminary Studymentioning

confidence: 99%

“…Because language and personality are strongly correlated, the use of seed words to categorize the topics according to human traits could be an alternative to overcome the inherent problems of collecting the personality-based datasets as the efforts to collect meaningful seed words are much cheaper and easier [5]. The recent literature also showed that incorporating seed knowledge to guide the auto-modeling is distributed in many aspects such as long documents [6], event detection and mapping [7], and unsupervised error estimation on various natural language text corpora [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Seed-Guided Latent Dirichlet Allocation Approach to Predict the Personality of Online Users Using the PEN Model

2022

View full text Add to dashboard Cite

There is a growing interest in topic modeling to decipher the valuable information embedded in natural texts. However, there are no studies training an unsupervised model to automatically categorize the social networks (SN) messages according to personality traits. Most of the existing literature relied on the Big 5 framework and psychological reports to recognize the personality of users. Furthermore, collecting datasets for other personality themes is an inherent problem that requires unprecedented time and human efforts, and it is bounded with privacy constraints. Alternatively, this study hypothesized that a small set of seed words is enough to decipher the psycholinguistics states encoded in texts, and the auxiliary knowledge could synergize the unsupervised model to categorize the messages according to human traits. Therefore, this study devised a dataless model called Seed-guided Latent Dirichlet Allocation (SLDA) to categorize the SN messages according to the PEN model that comprised Psychoticism, Extraversion, and Neuroticism traits. The intrinsic evaluations were conducted to determine the performance and disclose the nature of texts generated by SLDA, especially in the context of Psychoticism. The extrinsic evaluations were conducted using several machine learning classifiers to posit how well the topic model has identified latent semantic structure that persists over time in the training documents. The findings have shown that SLDA outperformed other models by attaining a coherence score up to 0.78, whereas the machine learning classifiers can achieve precision up to 0.993. We also will be shared the corpus generated by SLDA for further empirical studies.

show abstract

Section: Overview Of the Preliminary Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Seed-Guided Latent Dirichlet Allocation Approach to Predict the Personality of Online Users Using the PEN Model

2022

View full text Add to dashboard Cite

show abstract

“…Additionally, there are many previous supervised topic models that directly incorporate the supervision information into the unsupervised versions, including both works on single-label learning [21,14,38,39,35,36,29,24,26] and multi-label classification [32,27,28,30,13,17,25,37,1]. These models have empirically achieved very competitive classification performance, however, they require labeled documents as inputs.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, dataless text classification, i.e., a new paradigm of weakly supervised learning, has attracted increasing attention from the community [20,4,7,8,12,11,5,15,18,16,22,37,31,23]. The target is to build text classifiers by training over unlabeled documents with predefined representative words of categories (called seed words), instead of labeled documents.…”

Section: Introductionmentioning

confidence: 99%

Weakly Supervised Prototype Topic Model with Discriminative Seed Words: Modifying the Category Prior by Self-exploring Supervised Signals

Wang¹,

Wang²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Dataless text classification, i.e., a new paradigm of weakly supervised learning, refers to the task of learning with unlabeled documents and a few predefined representative words of categories, known as seed words. The recent generative dataless methods construct document-specific category priors by using seed word occurrences only, however, such category priors often contain very limited and even noisy supervised signals. To remedy this problem, in this paper we propose a novel formulation of category prior. First, for each document, we consider its label membership degree by not only counting seed word occurrences, but also using a novel prototype scheme, which captures pseudo-nearest neighboring categories. Second, for each label, we consider its frequency prior knowledge of the corpus, which is also a discriminative knowledge for classification. By incorporating the proposed category prior into the previous generative dataless method, we suggest a novel generative dataless method, namely Weakly Supervised Prototype Topic Model (Wsptm). The experimental results on real-world datasets demonstrate that Wsptm outperforms the existing baseline methods.

show abstract

“…It instead aligns anomaly patterns with human interests by leveraging human feedback Semi-supervised anomaly detection. Semi-supervised learning methods [27], [28] have been studied in the context of anomaly detection. Semi-supervised anomaly detection assumes that a small set of labeled instances can be used to improve the performance [29].…”

Section: Related Workmentioning

confidence: 99%

Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning

Zha

Lai

Wan

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

High false-positive rate is a long-standing challenge for anomaly detection algorithms, especially in high-stake applications. To identify the true anomalies, in practice, analysts or domain experts will be employed to investigate the top instances one by one in a ranked list of anomalies identified by an anomaly detection system. This verification procedure generates informative labels that can be leveraged to re-rank the anomalies so as to help the analyst to discover more true anomalies given a time budget. Some re-ranking strategies have been proposed to approximate the above sequential decision process. Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback. Then they greedily select the top-1 instance for query. However, these greedy strategies could be sub-optimal since some low-ranked instances could be more helpful in the long-term. Motivated by this, in this work, we study whether modeling long-term performance can benefit active anomaly detection. This is a challenging task because it is unclear how long-term performance could be quantified. In addition, the query selection has a huge decision space, which is difficult to model. To address these challenges, we propose Active Anomaly Detection with Meta-Policy (Meta-AAD), a novel framework that learns a metapolicy for query selection. Specifically, Meta-AAD leverages deep reinforcement learning to train the meta-policy to select the most proper instance to explicitly optimize the number of discovered anomalies throughout the querying process. Meta-AAD is easy to deploy since a trained meta-policy can be directly applied to any new datasets without further tuning. Extensive experiments on 24 benchmark datasets demonstrate that Meta-AAD significantly outperforms the state-of-the-art re-ranking strategies and the unsupervised baseline. The empirical analysis shows that the trained meta-policy is transferable and inherently achieves a balance between long-term and short-term rewards.

show abstract

Multi-label dataless text classification with topic modeling

Cited by 35 publications

References 35 publications

A Seed-Guided Latent Dirichlet Allocation Approach to Predict the Personality of Online Users Using the PEN Model

A Seed-Guided Latent Dirichlet Allocation Approach to Predict the Personality of Online Users Using the PEN Model

Weakly Supervised Prototype Topic Model with Discriminative Seed Words: Modifying the Category Prior by Self-exploring Supervised Signals

Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning

Contact Info

Product

Resources

About