See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/351972310 Natural Language Processing to Identify Trends and Gaps in the Published Science of Behavior Analysis Presentation · May 2021 DOI: 10.13140/RG.2.2.15624.34560 CITATIONS READS 0 10 2 authors: Jacob Sosine David J. Cox Behavioral Health Center of Excellence Behavioral Health Center of Excellence 2 PUBLICATIONS 8 CITATIONS 88 PUBLICATIONS 194 CITATIONS SEE PROFILE Some of the authors of this publication are also working on these related projects: Behavior Analysis for Ethics View project An evaluation of the role of extinction in a human operant model of resurgence View project All content following this page was uploaded by Jacob Sosine on 29 May 2021. The user has requested enhancement of the downloaded file. SEE PROFILE 5/29/21 Natural Language Processing to Identify Trends and Gaps in the Published Science of Behavior Analysis Jacob Sosine, M.A., M.B.A., BCBA David J. Cox, Ph.D., M.S.B., BCBA-D What is Natural Language Processing Data Pipeline How NLP can be used moving forward What is Natural Language Processing Intersection Between Artificial Intelligence and Linguistics Historically Apply Rules and Structure to Data More Recently 2 0 1 5 N LP M oved A w ay From S tatistical M od els Structural Linguistic Theories of VB N LP S tar ted L ookin g at the M ean in g or Fun ction Used Statistical Methods to Understand Language Techn iques are m ore related to the A n alysis of Ver bal B ehavior (Nadkarni et al., 2011) (Annamoradnejad et al., 2021) 1 5/29/21 What is Natural Language Processing Intersection Between Artificial Intelligence and Linguistics Allows Behavior Analysts to Study Verbal Behavior at Scale Every Day 2.5 quintillion bytes of data are uploaded 682 Million Tweets are Posted 4.3 Billion Facebook Messages are Sent A Lot of textual behavior! h3ps://blog.microfocus.com/how-much-data-is-created-on-the-internet-each-day What is Natural Language Processing Intersection Between Artificial Intelligence and Linguistics Allows Behavior Analysts to Study Verbal Behavior at Scale NLP has been utilized to …. Identify indicators of Child Abuse from Pediatric Medical Records Detect Humor in Sentences Classify Hate Speech on platforms like Twitter Summarize Text Answer Questions (Goa et al., 2019) What is Natural Language Processing NLP and Research Literature Explore and Visualize Bibliographic Data Predict Emerging Research Trends Inform Choice in Optimizing Research Designs (Rzhetsky et al., 2015) 2 5/29/21 What is Natural Language Processing Data Pipeline How NLP Can be Leveraged Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Topic Modeling Data Pipeline Data Gathering Automated Article Retrieval Simulated web browsing Gathered open access articles 3 5/29/21 Data Pipeline Data Gathering Automated Article Retrieval 4269 PDF’s Gathered 1958 - 2020 Data Pipeline Data Gathering Automated Article Retrieval 1152 PDF’s Gathered 1978 - 2020 Data Pipeline Data Gathering Automated Article Retrieval 3389 PDF’s Gathered 1968 - 2020 4 5/29/21 Data Pipeline Data Gathering Automated Article Retrieval 405 PDF’s Gathered 1982 - 2020 Data Pipeline Data Gathering Automated Article Retrieval 548 PDF’s Gathered 2008 - 2020 Data Pipeline Data Gathering Automated Article Retrieval 9763 Journal Articles 5 5/29/21 Data Pipeline Data Gathering Automated Article Retrieval 644 PDF’s Gathered 2016 - 2021 Health Service Research Data Pipeline Data Gathering Data Extraction 10,407 Data Pipeline Data Gathering Data Extraction 10,407 6 5/29/21 Data Pipeline Data Gathering Data Extraction Data Preprocessing Removes Noise from Our Dataset Allows a computer to interpret our inputs Data Pipeline Data Gathering Data Extraction “ The matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the fraction of hours per day you will spend eating, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging will throw a fastball, curve, slider, or changeup at this moment but the propor>on of each type of pitch he will throw to a given batter.” (Herrnstein R. J. 1977) Data Pipeline Data Gathering Data Extraction “ The matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac=on of hours per day you will spend ea=ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging will throw a fastball, curve, slider, or changeup at this moment but the proportion of each type of pitch he will throw to a given ba?er.” (Herrnstein R. J. 1977) Proper Nouns 7 5/29/21 Data Pipeline Data Gathering Data Extraction “ The matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac=on of hours per day you will spend ea=ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging will throw a fastball, curve, slider, or changeup at this moment but the proportion of each type of pitch he will throw to a given ba?er.” (Herrnstein R. J. 1977) Data Pipeline Data Gathering Data Extraction “The matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac=on of hours per day you will spend ea=ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase will throw a fastball, curve, slider, or changeup at this moment but the propor=on of each type of pitch he will throw to a given ba?er.” (Herrnstein R. J. 1977) Data Pipeline Data Gathering Data Extraction “ The matching law predicts not whether you will eat, ^ drink, sleep, play, or work at this very moment but the fraction of hours per day you will spend eating, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase will throw a fastball, curve, slider, or changeup at this moment but the propor>on of each type of pitch he will throw to a given batter.” (Herrnstein R. J. 1977) 8 5/29/21 Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac<on of hours per day you will spend ea<ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase will throw a fastball, curve, slider, or changeup at this moment but the proportion of each type of pitch he will throw to a given ba>er.” (Herrnstein R. J. 1977) Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the fraction of hours per day you will spend eating, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols will throw a fastball, curve, slider, or changeup at this moment but the propor=on of each type of pitch he will throw to a given batter.” (Herrnstein R. J. 1977) Data Pipeline Data Gathering Data Extraction Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols “the matching law predicts not whether you will eat, ^ drink, sleep, play, or work at this very moment but the ^ ^ ^ frac<on of hours per day you will spend ea<ng, drinking, ^ sleeping, playing, or working; not whether the pitcher ^ ^ will throw a fastball, curve, slider, or changeup at this ^ ^ ^ moment but the propor<on of each type of pitch he will throw to a given ba>er.” ^ (Herrnstein R. J. 1977) ^ ^ ^ ^ 9 5/29/21 Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac<on of hours per day you will spend ea<ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols will throw a fastball, curve, slider, or changeup at this moment but the propor<on of each type of pitch he will throw to a given ba>er.” (Herrnstein R. J. 1977) Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac<on of hours per day you will spend ea<ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols will throw a fastball, curve, slider, or changeup at this moment but the propor<on of each type of pitch he will throw to a given ba>er.” 4. Removing Stop Words & Numbers (Herrnstein R. J. 1977) (Fernández, et al., 2014) Data Pipeline Data Gathering Data Extraction Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols 4. Removing Stop Words & Numbers “the matching law predicts not whether you will eat, ^ ^ ^ drink, sleep, play, or work at this very moment but the ^ ^ ^ ^ ^ ^ frac<on of hours per day you will spend ea<ng, drinking, ^ ^ ^ sleeping, playing, or working; not whether the pitcher ^ ^ ^ will throw a fastball, curve, slider, or changeup at this ^ ^ ^ ^ ^ moment but the propor<on of each type of pitch he ^ ^ ^ ^ will throw to a given ba>er.” ^ ^ ^ ^ ^ (Herrnstein R. J. 1977) ^ (Fernández, et al., 2014) 10 5/29/21 Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the fraction of hours per day you will spend eating, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols will throw a fastball, curve, slider, or changeup at this moment but the propor=on of each type of pitch he will throw to a given batter.” 4. Removing Stop Words & Numbers (Herrnstein R. J. 1977) (Fernández, et al., 2014) Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac<on of hours per day you will spend ea<ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols will throw a fastball, curve, slider, or changeup at this moment but the proportion of each type of pitch he will throw to a given ba>er.” 4. Removing Stop Words & Numbers (Herrnstein R. J. 1977) 5. Word Tokenization Data Pipeline Data Gathering “the matching law predicts not whether you will eat, 1 2 3 4 5 6 drink, sleep, play, or work at this very moment but the Data Extraction 7 8 9 10 11 frac<on of hours per day you will spend ea<ng, drinking, 12 13 14 15 16 17 18 sleeping, playing, or working; not whether the pitcher Data Preprocessing 19 20 22 23 24 will throw a fastball, curve, slider, or changeup at this 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols 4. Removing Stop Words & Numbers 5. Word Tokenization 25 26 27 28 29 moment but the propor<on of each type of pitch he 30 31 will throw to a given ba>er.” 34 35 32 33 36 (Herrnstein R. J. 1977) 11 5/29/21 Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the fraction of hours per day you will spend eating, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols will throw a fastball, curve, slider, or changeup at this moment but the propor=on of each type of pitch he will throw to a given ba>er.” 4. Removing Stop Words & Numbers (Herrnstein R. J. 1977) 5. Word Tokenization 6. Lemmatization Data Pipeline Data Gathering Data Extraction Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac<on of hours per day you will spend ea<ng, drinking, ^ sleeping, playing, or working; not whether the pitcher will throw a fastball, curve, slider, or changeup at this moment but the propor<on of each type of pitch he will throw to a given ba>er.” 4. Removing Stop Words & Numbers (Herrnstein R. J. 1977) 5. Word Tokenization 6. Lemmatization Data Pipeline Data Gathering Data Extraction “the matching law predicts not whether you will eat, drink, sleep, play, or work at this very moment but the frac<on of hours per day you will spend ea<ng, drinking, sleeping, playing, or working; not whether the pitcher Data Preprocessing 1. Part of Speech Tagging 2. Lowercase 3. Remove Punctuation & Symbols 4. Removing Stop Words & Numbers 5. Word Tokenization will throw a fastball, curve, slider, or changeup at this moment but the proportion of each type of pitch he will throw to a given ba>er.” (Herrnstein R. J. 1977) 6. Lemmatization 12 5/29/21 Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Data Pipeline MEDIAN Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis 13 5/29/21 Data Pipeline 50% of Data on article count Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Data Pipeline Data Gathering Data Extraction Individual Article Word Counts Data Preprocessing Exploratory Data Analysis Data Pipeline Data Gathering Data Extraction Data Preprocessing Compare Distributions Exploratory Data Analysis 14 5/29/21 Data Pipeline Data Pipeline 15 5/29/21 Data Pipeline Data Pipeline Data Gathering Data Extraction Scattertext Visualization Uses 2 data Sources higher up the w ord is on the y-axis, the m ore it w as used by data source 1. Data Preprocessing Topic Modeling Y Exploratory Data Analysis X Data Pipeline Data Gathering Data Extraction Scattertext Visualization Uses 2 data Sources The further right on the X axis The more it is used by data source 2 Data Preprocessing Topic Modeling Y Exploratory Data Analysis X 16 5/29/21 Data Pipeline Data Gathering Data Extraction Scattertext Visualization Uses 2 data Sources Frequently used terms by both sources appear in the top right of the graph Data Preprocessing Topic Modeling Y Exploratory Data Analysis X Data Pipeline Data Gathering Data Extraction Scattertext Visualization Uses 2 data Sources Infrequently used terms by both sources appear in the bottom left of the graph Data Preprocessing Topic Modeling Y Exploratory Data Analysis X Data Pipeline Data Gathering Data Extraction Scattertext Visualization Uses 2 data Sources Each Data Point Represents a Word and Includes a label Data Preprocessing Topic Modeling Y Exploratory Data Analysis X 17 5/29/21 Top 500 Words 18 5/29/21 Most Frequent JABA Most Frequent JEAB 19 5/29/21 20 5/29/21 Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Topic Modeling Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Topic Modeling 21 5/29/21 Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Unsupervised Machine Learning Hidden Semantic Structure Matching Law Choice Rate of Reinforcement Concurrent Schedules of Reinforcement Topic Modeling Data Pipeline Data Gathering Data Extraction Data Preprocessing Exploratory Data Analysis Topic Modeling Topic Model Visualizations Include Topic Bubble Each Bubble Represents a Topic The Further Away the Bubble the More Different the topic is Horizontal Stacked Bar Chart Blue Bars = Overall Frequency of Each Word in our Dataset Red Bars = Number of times a given term is generated in a topic = rank terms according to term relevance λ slider 22 5/29/21 What is Natural Language Processing What is Natural Language Processing Data Pipeline 23 5/29/21 What is Natural Language Processing Data Pipeline Data Collection and Transformation Visually Inspect Textual Data Recognize Similarities and Differences between our verbal communities Quantify Topics in Behavior Analytic Research What is Natural Language Processing Data Pipeline Only Able to Review Published Journal Articles Largely a Result of Complex Behavior Chains U n able to brin g in A n teced en ts an d Con sequen ces in to our an alysis What is Natural Language Processing Data Pipeline … I have also read books, not for what they said about verbal behavior, but as records of verbal behavior. I have done my share of comma-counting. I have listened to people speaking and jotted down slips, curious phrases, or interesting intraverbal sequences… (Skinner, 1957, p. 454 ) 24 5/29/21 What is Natural Language Processing Data Pipeline How NLP can be used moving forward ! " # $ 0 1 0 1 0 1 0 1 0 1 0 1 1 1 0 1 0 1 1 1 What is Natural Language Processing Data Pipeline How NLP can be used moving forward ! 0 1 0 1 0 1 0 1 0 1 0 1 1 1 0 1 0 1 1 1 0 1 0 1 0 1 0 1 0 1 0 1 1 1 0 1 0 1 1 1 What is Natural Language Processing Data Pipeline How NLP can be used moving forward Mands Tacts Autoclitics ! 25 5/29/21 What is Natural Language Processing Data Pipeline How NLP can be used moving forward Even in its simplest applications NLP can increase our understanding of behavior Leveraging this technology can allow researchers to ask and answer different research questions NLP is an accessible tool for Behavior Analysts What is Natural Language Processing Data Pipeline How NLP can be used moving forward Even in its simplest applications NLP can increase our understanding of behavior Leveraging this technology can allow researchers to ask and answer different research questions NLP is an accessible tool for Behavior Analysts References • H e r r n s te in , R . J . ( 1 9 9 7 ) . T h e m a tc h in g la w : P a p e r s in p s y c h o lo g y a n d e c o n o m ic s . ( H . R a c h lin & D . I. L a ib s o n , E d s .) . R u s s e ll S a g e F o u n d a tio n ; H a r v a r d U n iv e r s ity P r e s s . • B le i, D . M . ( 2 0 1 2 ) . P r o b a b ilis tic to p ic m o d e ls . C o m m u n ic a tio n s o f th e A C M , 5 5 ( 4 ) , 7 7 - 8 4 . • S a i f , H a s s a n ; F e r n á n d e z , M i r i a m ; H e , Y u l a n a n d A l a n i , H a r i t h ( 2 0 1 4 ) . O n s t o p w o r d s , f i l t e r i n g a n d d a t a s p a r s i t y f o r s e n t i m e n t a n a l y s i s o f T w i t t e r. I n : L R E C 2 0 1 4 , N i n t h I n t e r n a t i o n a l C o n f e r e n c e o n L a n g u a g e R e s o u r c e s a n d E v a l u a t i o n . P r o c e e d i n g s . , p p . 8 1 0 – 8 1 7 . • S k i n n e r, B . F . ( 1 9 5 7 ) . V e r b a l b e h a v i o r . N e w Y o r k : A p p l e t o n - C e n t u r y - C r o f t s . • A n n a m o r a d n e ja d , I., Z o g h i, G . ( 2 0 2 1 ) . C o lB e r t: U s in g B E R T s e n te n c e e m b e d d in g fo r h u m o r d e te c tio n . C o m p u ta tio n a n d L a n g u a g e . 1 - 6 . • D a v i d s o n , T . , W a r m s l e y , D . , M a c y , M . , & W e b e r, I . , ( 2 0 1 7 ) . A u t o m a t e d h a t e s p e e c h d e t e c t i o n a n d t h e p r o b l e m o f o ff e n s i v e l a n g u a g e . I C W S M . 1 - 3 • N a d k a r n i, P. M ., O h n o - M a c h a d o , L ., & C h a p m a n , W . W . ( 2 0 1 1 ) . N a tu r a l la n g u a g e p r o c e s s in g : a n in tr o d u c tio n . J o u r n a l o f th e A m e r ic a n M e d ic a l In fo r m a tic s A s s o c ia tio n , 1 8 ( 5 ) , 5 4 4 – 5 5 1 . h ttp s ://d o i.o r g /1 0 .1 1 3 6 /a m ia jn l- 2 0 1 1 - 0 0 0 4 6 4 • A n n a p r a g a d a A V , D o n a r u m a - K w o h M M , A n n a p r a g a d a A V , S ta r o s o ls k i Z A ( 2 0 2 1 ) A n a tu r a l la n g u a g e p r o c e s s in g a n d d e e p le a r n in g a p p r o a c h to id e n tify c h ild a b u s e fr o m p e d ia tr ic e le c tr o n ic m e d ic a l r e c o r d s . P L o S O N E 1 6 ( 2 ) : e 0 2 4 7 4 0 4 . h ttp s ://d o i.o r g /1 0 .1 3 7 1 /jo u r n a l.p o n e .0 2 4 7 4 0 4 • M u k ta fin , E ., K u s r in i, P. ( 2 0 2 0 ) . S e n tim e n ts a n a ly s is o f c u s to m e r s a tis fa c tio n in p u b lic s e r v ic e s u s in g K - n e a r e s t n e ig h b o r s a lg o r ith m a n d n a tu r a l la n g u a g e p r o c e s s in g a p p r o a c h . T E L K O M N IK A T e le c o m m u n ic a tio n , C o m p u tin g , E le c tr o n ic s a n d C o n tr o l. 1 9 ( 1 ) ,1 4 6 - 1 5 4 . • P e n g , J . , Z h a o , M . , H a v r i l l a , J . , L i u , C . , W e n g , C . , G u t h r i e , W . , S c h u l t z , R . , W a n g , K . , & Z h o u , Y . ( 2 0 2 0 ) . N a t u r a l l a n g u a g e p r o c e s s i n g ( N L P ) t o o l s i n e x t r a c t i n g b i o m e d i c a l c o n c e p t s f r o m r e s e a r c h a r t i c l e s : a c a s e s t u d y o n a u t i s m s p e c t r u m d i s o r d e r. B M C M e d i c a l I n f o r m a t i c s a n d D e c i s i o n M a k i n g . 2 0 (11 ), 3 -9 . • T o m a n , M . , T e s a r, R . , J e z e k , K . , ( 2 0 1 4 ) . I n f l u e n c e o f w o r d n o r m a l i z a t i o n o n t e x t c l a s s i f i c a t i o n . • K n ig h t, K ., M a r c u , D ., ( 2 0 0 2 ) . S u m m a r iz a tio n b e y o n d s e n te n c e e x tr a c tio n : a p r o b a b ilis tic a p p r o a c h to s e n te n c e c o m p r e s s io n . A r tific ia l In te llig e n c e . 1 3 9 . • B le i, D ., C a r in , L ., D u n s o n , D . ( 2 0 1 0 ) . P r o b a b ilis tic to p ic m o d e ls : A fo c u s o n g r a p h ic a l m o d e l d e s ig n a n d a p p lic a tio n s to d o c u m e n t a n d im a g e a n a ly s is . IE E E S ig n a l P r o c e s s M a g . 2 7 ( 6 ) : 5 5 - 6 5 . d o i: 1 0 .1 1 0 9 /M S P.2 0 1 0 .9 3 8 0 7 9 • A s m u s s e n , C . B . , M o l l e r, C . ( 2 0 1 9 ) . S m a r t l i t e r a t u r e r e v i e w : a p r a c t i c a l t o p i c m o d e l i n g a p p r o a c h t o e x p l o r a t o r y l i t e r a t u r e r e v i e w . J o u r n a l o f B i g D a t a 9 3 ( 6 ) : 2 - 1 8 . d o i : h t t p s : / / d o i . o r g / 1 0 . 1 1 8 6 / s 4 0 5 3 7 - 0 1 9 - 0 2 5 5 - 7 • J o h n s o n , M ., ( 2 0 0 9 ) H o w th e s ta tis tic a l r e v o lu tio n c h a n g e s ( c o m p u ta tio n a l) lin g u is tic s . C o g n ifiv e a n d L in g u is tic S c ie n c e s a n d C o m p u te r S c ie n c e . 3 - 1 1 . • F r a n c o p o u lo G ., M a r ia n i, J ., P a r o u b e k , P. ( 2 0 1 6 ) . A s tu d y o f r e u s e a n d p la g ia r is m in L R E C p a p e r s . E u r o p e a n L a n g u a g e R e s o u r c e s A s s o c ia tio n ( E L R A ) . 1 8 9 0 - 1 8 9 7 • F r a n c o p o u lo G ., M a r ia n i, J ., P a r o u b e k , P. ( 2 0 1 6 ) . P r e d ic tiv e m o d e lin g : g u e s s in g th e N L P te r m s o f to m o r r o w . E u r o p e a n L a n g u a g e R e s o u r c e s A s s o c ia tio n ( E L R A ) . 3 3 6 – 3 4 3 • K r e n n . M . , & Z e i l i n g e r, A . ( 2 0 2 0 ) . P r e d i c t i n g R e s e a r c h T r e n d s w i t h S e m a n t i c a n d N e u r a l N e t w o r k s w i t h a n a p p l i c a t i o n i n Q u a n t u m P h y s i c s . P r o c e e d i n g s o f t h e N a t i o n a l A c a d e m y o f S c i e n c e s . 1 1 7 ( 4 ) . 1 - 1 5 . • Rzhetsky, A., Foster, J.G., Foster, I ., Evans, J. A. (2015). Choosing experiments to accelerate collecEve discovery . Proceedings of the Na1onal Academy of Sciences . 10.1073/pnas.1509757112 • Cabanac, G., Frommholz, I., M ayr, P. (2018). Bibliometric-enhanced informaEon retrieval. Scientometrics 116:1225–1227 26 5/29/21 Thank You! Lin ked In : https://w w w .lin ked in .com /in /jacob- sosin e- a0 5 9 9 4 8 a/ R esearch G ate: h"ps://w w w.researchgate.net/proļ¬le/Jacob-Sosine E m ail: jacobsosine@ gm ail.com 27 View publication stats