Innovation Novelty and Firm Value: Deep Learning based Text Understanding

Wei HU; Yuk Yee CHAN; Jianming HUANG; Wanyue Zhou; Xin Li

Innovation Novelty and Firm Value: Deep Learning based Text Understanding

Wei HU^*, Yuk Yee CHAN, Jianming HUANG, Wanyue Zhou, Xin Li

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Innovation is widely acknowledged as a key driver of firm performance, with patents serving as unique indicators of a company’s technological advancements. This study aims to investigate the impact of textual novelty within patents on firm performance, focusing specifically on biotechnology startups listed on the Nasdaq. Utilizing deep learning-based approaches, we construct measures for semantic originality in patent texts. Through panel vector autoregressive (VAR) analysis, our empirical findings demonstrate a positive correlation between textual novelty and abnormal stock returns. Further, impulse response function analysis indicates that the impact of textual novelty peaks approximately one week after patent issuance and gradually diminishes within a month. These insights offer valuable contributions to both the theoretical understanding and practical application of innovation management and strategic planning.

Original language	English
Title of host publication	ICIS 2023 Proceedings
Publisher	Association for Information Systems
ISBN (Electronic)	9781958200070
ISBN (Print)	9781713893622
Publication status	Published - 2023
Event	44th International Conference on Information Systems (ICIS 2023) - Hyderabad, India Duration: 10 Dec 2023 → 13 Dec 2023 https://icis2023.aisconferences.org/ https://aisel.aisnet.org/icis2023/

Conference

Conference	44th International Conference on Information Systems (ICIS 2023)
Abbreviated title	ICIS
Place	India
City	Hyderabad
Period	10/12/23 → 13/12/23
Internet address	https://icis2023.aisconferences.org/ https://aisel.aisnet.org/icis2023/

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Research Keywords

Innovation
patent
text analysis
stock market
deep learning

Access Output

https://aisel.aisnet.org/icis2023/dab_sc/dab_sc/8

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{d2f14df9c19e4a21a8cd8df65a1ef8d4,

title = "Innovation Novelty and Firm Value: Deep Learning based Text Understanding",

abstract = "Innovation is widely acknowledged as a key driver of firm performance, with patents serving as unique indicators of a company{\textquoteright}s technological advancements. This study aims to investigate the impact of textual novelty within patents on firm performance, focusing specifically on biotechnology startups listed on the Nasdaq. Utilizing deep learning-based approaches, we construct measures for semantic originality in patent texts. Through panel vector autoregressive (VAR) analysis, our empirical findings demonstrate a positive correlation between textual novelty and abnormal stock returns. Further, impulse response function analysis indicates that the impact of textual novelty peaks approximately one week after patent issuance and gradually diminishes within a month. These insights offer valuable contributions to both the theoretical understanding and practical application of innovation management and strategic planning.",

keywords = "Innovation, patent, text analysis, stock market, deep learning",

author = "Wei HU and CHAN, {Yuk Yee} and Jianming HUANG and Wanyue Zhou and Xin Li",

note = "Research Unit(s) information for this publication is provided by the author(s) concerned.; 44th International Conference on Information Systems (ICIS 2023), ICIS ; Conference date: 10-12-2023 Through 13-12-2023",

year = "2023",

language = "English",

isbn = "9781713893622",

booktitle = "ICIS 2023 Proceedings",

publisher = "Association for Information Systems",

address = "United States",

url = "https://icis2023.aisconferences.org/, https://aisel.aisnet.org/icis2023/",

}

TY - GEN

T1 - Innovation Novelty and Firm Value

T2 - 44th International Conference on Information Systems (ICIS 2023)

AU - HU, Wei

AU - CHAN, Yuk Yee

AU - HUANG, Jianming

AU - Zhou, Wanyue

AU - Li, Xin

N1 - Research Unit(s) information for this publication is provided by the author(s) concerned.

PY - 2023

Y1 - 2023

N2 - Innovation is widely acknowledged as a key driver of firm performance, with patents serving as unique indicators of a company’s technological advancements. This study aims to investigate the impact of textual novelty within patents on firm performance, focusing specifically on biotechnology startups listed on the Nasdaq. Utilizing deep learning-based approaches, we construct measures for semantic originality in patent texts. Through panel vector autoregressive (VAR) analysis, our empirical findings demonstrate a positive correlation between textual novelty and abnormal stock returns. Further, impulse response function analysis indicates that the impact of textual novelty peaks approximately one week after patent issuance and gradually diminishes within a month. These insights offer valuable contributions to both the theoretical understanding and practical application of innovation management and strategic planning.

AB - Innovation is widely acknowledged as a key driver of firm performance, with patents serving as unique indicators of a company’s technological advancements. This study aims to investigate the impact of textual novelty within patents on firm performance, focusing specifically on biotechnology startups listed on the Nasdaq. Utilizing deep learning-based approaches, we construct measures for semantic originality in patent texts. Through panel vector autoregressive (VAR) analysis, our empirical findings demonstrate a positive correlation between textual novelty and abnormal stock returns. Further, impulse response function analysis indicates that the impact of textual novelty peaks approximately one week after patent issuance and gradually diminishes within a month. These insights offer valuable contributions to both the theoretical understanding and practical application of innovation management and strategic planning.

KW - Innovation

KW - patent

KW - text analysis

KW - stock market

KW - deep learning

UR - http://www.scopus.com/inward/record.url?scp=85192527171&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85192527171&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781713893622

BT - ICIS 2023 Proceedings

PB - Association for Information Systems

Y2 - 10 December 2023 through 13 December 2023

ER -

Innovation Novelty and Firm Value: Deep Learning based Text Understanding

Abstract

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this