An alternative topic model based on Common Interest Authors for topic evolution analysis

Jung, Sukhwan; Yoon, Wan Chul

doi:10.1016/j.joi.2020.101040

Cited by 32 publications

(17 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While these approaches allow detection of merging and splitting of time-spanning topics and their transitional ratio at the temporal level, the use of text-based topic models inherently limits predictive capabilities; evolutionary events such as emerge, merge, or split can only be retrospectively analyzed once topics are captured from a document set. Using author groups from a bibliographic dataset for determining topics carried over time by the evolving author groups showed that when topics defined by the authors are used instead of NLP-based topic models, topic evolution on the temporal network is possible; the topic evolution events are defined by network structures, and therefore a predictive analysis is possible [23].…”

Section: Identifying and Predicting New Topicsmentioning

confidence: 99%

“…Traditional topic evolution methods mimic the process by utilizing text-based topic models to understand topics in each document collection and track topical changes over time. Topic modeling methods extract statistical constructs based on word co-occurrences in the given document collection, where changes in topics can only be measured by differences between the content of two topics; connections and correlations between different topics are not incorporated into traditional topic modeling methods [23]. Topic evolution methods are therefore mostly limited to identifying content transition within a given topic, not how it is correlated to other topics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analyzing the generalizability of the network-based topic emergence identification method

Jung

Segev

2022

Self Cite

View full text Add to dashboard Cite

Topic evolution helps the understanding of current research topics and their histories by automatically modeling and detecting the set of shared research fields in academic publications as topics. This paper provides a generalized analysis of the topic evolution method for predicting the emergence of new topics, which can operate on any dataset where the topics are defined as the relationships of their neighborhoods in the past by extrapolating to the future topics. Twenty sample topic networks were built with various fields-of-study keywords as seeds, covering domains such as business, materials, diseases, and computer science from the Microsoft Academic Graph dataset. The binary classifier was trained for each topic network using 15 structural features of emerging and existing topics and consistently resulted in accuracy and F1 over 0.91 for all twenty datasets over the periods of 2000 to 2019. Feature selection showed that the models retained most of the performance with only one-third of the tested features. Incremental learning was tested within the same topic over time and between different topics, which resulted in slight performance improvements in both cases. This indicates there is an underlying pattern to the neighbors of new topics common to research domains, likely beyond the sample topics used in the experiment. The result showed that network-based new topic prediction can be applied to various research domains with different research patterns.

show abstract

Section: Identifying and Predicting New Topicsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analyzing the generalizability of the network-based topic emergence identification method

Jung

Segev

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The formation of a single topic is thus proceeded by conver the words with a high probability contribution, and if the number of words under a t is too high or low, the interpretation of the deduced topic will be difficult. If the num of topics is too high or low, the words within each topic may be duplicated to be e nated or the topic may show a reduced correlation to pose challenges in interpreta Many researchers who utilize topic-modeling methods point out that loss of interpret ity is a major limitation of complex learning algorithms such as topic models, that say, it is important to note that topics produced by complex algorithms are numeric va based on mathematical properties, but the interpretation of them depends on the goa the analysis, the researcher's perspectives and domain knowledge [35][36][37][38]. Thus, the perparameter, as directly set by the user, should allow the optimum number to be d mined through several reasonable attempts based on the experimental values or sc for the topics to be deduced.…”

Section: Lda Topic Modelingmentioning

confidence: 99%

Determination of Motivating Factors of Urban Forest Visitors through Latent Dirichlet Allocation Topic Modeling

Kim

Lee

Park

2021

IJERPH

View full text Add to dashboard Cite

Despite the unique characteristics of urban forests, the motivating factors of urban forest visitors have not been clearly differentiated from other types of the forest resource. This study aims to identify the motivating factors of urban forest visitors, using latent Dirichlet allocation (LDA) topic modeling based on social big data. A total of 57,449 cases of social text data from social blogs containing the keyword “urban forest” were collected from Naver and Daum, the major search engines in South Korea. Then, 17,229 cases were excluded using morpheme analysis and stop word elimination; 40,110 cases were analyzed to identify the motivating factors of urban forest visitors through LDA topic modeling. Seven motivating factors—“Cafe-related Walk”, “Healing Trip”, “Daily Leisure”, “Family Trip”, “Wonderful View”, “Clean Space”, and “Exhibition and Photography”—were extracted; each contained five keywords. This study elucidates the role of forests as a place for healing, leisure, and daily exercise. The results suggest that efforts should be made toward developing various programs regarding the basic functionality of urban forests as a natural resource and a unique place to support a diversity of leisure and cultural activities.

show abstract

“…An example of M is given in Table 4. To estimate TESs in M, the concept of similarity has been widely used in most related works [9,5,11,16,1,3]. The fundamental is to formulate a similarity measure between x and y using the aggregated similarities between x's top-k descriptive terms and y's top-k descriptive terms (often K=10) [19,3].…”

Section: Input Data Formatmentioning

confidence: 99%

TopicTracker: A Platform for Topic Trajectory Identification and Visualisation

Kang,

Sellis

2021

Preprint

View full text Add to dashboard Cite

Topic trajectory information provides crucial insight into the dynamics of topics and their evolutionary relationships over a given time. Also, this information can help to improve our understanding on how new topics have emerged or formed through a sequential or interrelated events of emergence, modification and integration of prior topics. Nevertheless, the implementation of the existing methods for topic trajectory identification is rarely available as usable software. In this paper, we present TopicTracker, a platform for topic trajectory identification and visualisation.The key of TopicTracker is that it can represent the three facets of information together, given two kinds of input: a time-stamped topic profile consisting of the set of the underlying topics over time, and the evolution strength matrix among them: evolutionary pathways of dynamic topics, evolution states of the topics, and topic importance. TopicTracker is a publicly available software implemented using the R software.

show abstract

An alternative topic model based on Common Interest Authors for topic evolution analysis

Cited by 32 publications

References 42 publications

Analyzing the generalizability of the network-based topic emergence identification method

Analyzing the generalizability of the network-based topic emergence identification method

Determination of Motivating Factors of Urban Forest Visitors through Latent Dirichlet Allocation Topic Modeling

TopicTracker: A Platform for Topic Trajectory Identification and Visualisation

Contact Info

Product

Resources

About