The investigation of vehicle defects, which is generally led by the National Highway Traffic Safety Administration (NHTSA) in the U.S., is critical to the continued trust of the general public in the safety of vehicles. NHTSA routinely receives millions of reports of potential defects, complaints, recalls, and manufacturer communications, which may provide evidence of a new vehicle defect. However, the large quantity and text-based communication make efficiently identifying defect trends difficult for analysts. To accelerate the investigation of defect reports, we introduce a natural language processing (NLP) application that identifies key topics and similar defect reports to assist analysts and investigators. Further, our application is built to provide users with a web interface for interacting with the NLP models. The integration of NLP with current NHTSA datasets provides a method for quickly identifying defect trends in large text-based datasets. To demonstrate the effectiveness of our method, we apply our approach to two publicly available NHTSA datasets, namely the Technical Service Bulletins and Recalls Dataset.
Transportation Research Board Artificial Intelligence Committee. A Primer on Machine Learning for Transportation. Presented at Annual Meeting of the Transportation Research Board, Washington, D.C., 2020.
2.
WuC.KreidiehA.ParvateK.VinitskyE.BayenA. M.Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control. arXiv Preprint arXiv:1710.05465, 2017.
3.
BoothJ.Di EugenioB.CruzI. F.WolfsonO.Robust Natural Language Processing for Urban Trip Planning. Applied Artificial Intelligence, Vol. 29, No. 9, 2015, pp. 859–903.
4.
BaruaL.ZouB.ZhouY.Machine Learning for International Freight Transportation Management: A Comprehensive Review. Research in Transportation Business & Management, Vol. 34, 2020, pp. 1004–1053.
5.
SligarA. P.Machine Learning-Based Radar Perception for Autonomous Vehicles Using Full Physics Simulation. IEEE Access, Vol. 8, 2020, pp. 51470–51476.
6.
AtaA.KhanM. A.AbbasS.KhanM. S.AhmadG.Adaptive IoT Empowered Smart Road Traffic Congestion Control System Using Supervised Machine Learning Algorithm. The Computer Journal, Vol. 64, No. 11, 2021, pp. 1672–1679.
7.
YangJ.LiS.WangZ.DongH.WangJ.TangS.Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges. Materials, Vol. 13, 2020, p. 5755.
8.
LiqunW.JianshengW.DingjinW.Research on Vehicle Parts Defect Detection Based on Deep Learning. Journal of Physics: Conference Series, Vol. 1437, No. 1, 2020, p. 012004.
9.
NadkarniP. M.Ohno-MachadoL.ChapmanW. W.Natural Language Processing: An Introduction. Journal of the American Medical Informatics Association, Vol. 18, No. 5, 2011, pp. 544–551.
10.
NHTSA. Risk-Based Processes for Safety Defect Analysis and Management of Recalls. NHTSA, Washington, D.C., 2020.
11.
NHTSA. General Standard Operating Procedures (SOP). NHTSA, Washington, D.C., 2017.
12.
RussellS.NorvigP. (eds.). Chapter 23: Natural Language Processing. In Artificial Intelligence: A Modern Approach, 4th ed, Pearson Education, London, UK, 2020, pp. 823–855.
13.
MikolovT.ChenK.CorradoG.DeanJ.Efficient Estimation of Word Representations in Vector Space. arXiv Preprint arXiv:1301.3781, 2013.
14.
LeQ.MikolovT.Distributed Representations of Sentences and Documents. Proc., International Conference on Machine Learning, Beijing, China, 2014.
15.
RamosJ.Using TF-IDF to Determine Word Relevance in Document Queries. Proc., 1st Instructional Conference on Machine Learning, Vol. 242, 2003, pp. 133–142.
16.
BleiD. M.NgA. Y.JordanM. I.Latent Dirichlet Allocation. Journal of Machine Learning Research, Vol. 3, 2003, p. 993–1022.
17.
WolfT.DebutL.SanhV.ChaumondJ.DelangueC.MoiA.CistacP., et al. Huggingface’s Transformers: State-of-the-Art Natural Language Processing. arXiv Preprint arXiv:1910.03771, 2019.
18.
DevlinJ.ChangM.-W.LeeK.ToutanovaK.Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding. arXiv Preprint arXiv:1810.04805, 2018.
19.
PetersM. E.NeumannM.IyyerM.GardnerM.ClarkC.LeeK.ZettlemoyerL.Deep Contextualized Word Representations. arXiv Preprint arXiv:1802.05365, 2018.
20.
BrownT. B.MannB.RyderN.SubbiahM.KaplanJ.DhariwalP.NeelakantanA., et al. Language Models are Few-Shot Learners. arXiv Preprint arXiv:2005.14165, 2020.
21.
HoulsbyN.GiurgiuA.JastrzebskiS.MorroneB.De LaroussilheQ.GesmundoA.AttariyanM.GellyS.Parameter-Efficient Transfer Learning for NLP. Proc., International Conference on Machine Learning, Long Beach, CA, 2019.
22.
LeeJ.YoonW.KimS.KimD.KimS.SoC. H.KangJ.BioBERT: A Pre-Trained Biomedical Language Representation Model for Biomedical Text Mining. Bioinformatics, Vol. 36, No. 4, 2020, pp. 1234–1240.
23.
ChalkidisI.FergadiotisM.MalakasiotisP.AletrasN.AndroutsopoulosI.LEGAL-BERT: The Muppets Straight out of Law School. arXiv Preprint arXiv:2010.02559, 2020.
24.
GurcanF.CagiltayN. E.Big Data Software Engineering: Analysis of Knowledge Domains and Skill Sets Using LDA-Based Topic Modeling. IEEE Access, Vol. 7, 2019, pp. 82541–82552.
25.
JelodarH.WangY.YuanC.FengX.JiangX.LiY.ZhaoL.Latent Dirichlet Allocation (LDA) and Topic Modeling: Models, Applications, a Survey. Multimedia Tools and Applications, Vol. 78, No. 11, 2019, pp. 15169–15211.
26.
LiuL.TangL.DongW.YaoS.ZhouW.An Overview of Topic Modeling and its Current Applications in Bioinformatics. SpringerPlus, Vol. 5, No. 1, 2016, pp. 1–22.
27.
AlambeigiH.McDonaldA. D.TankasalaS. R.Crash Themes in Automated Vehicles: A Topic Modeling Analysis of the California Department of Motor Vehicles Automated Vehicle Crash Database. arXiv Preprint arXiv:2001.11087, 2020.
28.
HaveliwalaT. H.GionisA.KleinD.IndykP.Evaluating Strategies for Similarity Search on the Web. Proc., 11th International Conference on World Wide Web, Honolulu, HI, 2002.
29.
AkhbardehF.DesellT.ZampieriM.NLP Tools for Predictive Maintenance Records in MaintNet. Proc., 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: System Demonstrations, Suzhou, China, 2020.
30.
McEwanR.MeltonG. B.KnollB. C.WangY.HultmanG.DaleJ. L.MeyerT.PakhomovS. V.NLP-PIER: A Scalable Natural Language Processing, Indexing, and Searching Architecture for Clinical Notes. AMIA Summits on Translational Science Proceedings, Vol. 2016, 2016, p. 150.
31.
KannanS.GurusamyV.VijayaraniS.IlamathiJ.NithyaM.KannanS.GurusamyV.Preprocessing Techniques for Text Mining. International Journal of Computer Science & Communication Networks, Vol. 5, No. 1, 2014, pp. 7–16.
32.
BirdS.LoperE.EwanK.Natural Language Processing With Python. O’Reilly Media Inc., Sebastopol, CA, 2009.
33.
GriffithsT. L.SteyversM.Finding Scientific Topics. Proceedings of the National Academy of Sciences, Vol. 101, 2004, pp. 5228–5235.
34.
OghbaieM.ZanjirehM. M.Pairwise Document Similarity Measure Based on Present Term Set. Journal of Big Data, Vol. 5, 2018, pp. 1–23.
35.
Maslej-KrešňákováV.SarnovskỳM.ButkaP.MachováK.Comparison of Deep Learning Models and Various Text Pre-Processing Techniques for the Toxic Comments Classification. Applied Sciences, Vol. 10, 2020, p. 8631.
36.
VaswaniA.ShazeerN.ParmarN.UszkoreitJ.JonesL.GomezA. N.KaiserŁ.PolosukhinI.Attention is all you Need. In Advances in Neural Information Processing Systems (GuyonI.Von LuxburgU.BengioS.WallachH.FergusR.VishwanathanS.GarnettR., eds.), 2017.
37.
ClarkK.KhandelwalU.LevyO.ManningC. D.What Does BERT Look At? An Analysis of BERT’s Attention. arXiv Preprint arXiv:1906.04341, 2019.
38.
PengY.YanS.LuZ.Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets. arXiv Preprint arXiv:1906.05474, 2019.
39.
MozafariM.FarahbakhshR.CrespiN.A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media. In Proc., Complex Networks 2019: International Conference on Complex Networks and Their Applications (CherifiH.GaitoS.MendesJ.MoroE.RochaL., eds.), Lisbon, Portugal, December 10–12, 2019, Springer, Cham, pp. 928–940.
40.
SunC.XipengQ.YigeX.XuanjingH.How to Fine-Tune BERT for Text Classification? In Proc., Chinese Computational Linguistics: China National Conference on Chinese Computational Linguistics (SunM.HuangX.JiH.LiuZ.LiuY., eds.), Kunming, China, October 18–20, 2019, Springer, Cham, pp. 194–206.
41.
ReimersN.GurevychI.Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks. Proc., 2019 Conference on Empirical Methods in Natural Language Processing, Hong Kong, China, 2019.
42.
PedregosaF.VaroquauxG.GramfortA.MichelV.ThirionB.GriselO.BlondelM., et al. Scikit-Learn: Machine Learning in Python. Journal of Machine Learning Research, Vol. 12, 2011, pp. 2825–2830.
43.
GholizadehS.SavleK.SeyeditabariA.ZadroznyW.Topological Data Analysis in Text Classification: Extracting Features With Additive Information. arXiv Preprint arXiv:2003.13138, 2020.
