About relationship between business text patterns and financial performance in corporate data

Lee, BangRae; Park, Jun-Hwan; Kwon, Leenam; Moon, Young-Ho; Shin, YoungHo; Kim, GyuSeok; Kim, Han-joon

doi:10.1186/s40852-018-0080-9

Journal of Open Innovation: Technology, Market, and Complexity

Table 6 Non-overlapped and overlapped top 50 keywords from the two cases

From: About relationship between business text patterns and financial performance in corporate data

No.	H-word	TF-IDF※	Inter-word	TF-IDF※	L-word	TF-IDF※
1	users	1052	may	3510	contracts	684
2	advertising	975	business	2184	government	619
3	platform	880	services	1702	leidos	354
4	data	854	products	1569	contract	346
5	user	679	results	1351	revenues	317
6	content	640	including	1228	assets	242
7	advertisers	601	future	1221	profitability	232
8	members	599	operating	1221	customer	230
9	notes	568	will	1201	technologies	229
10	access	558	result	1201	process	228
11	class	523	new	1199	programs	222
12	clients	522	stock	1169	fiscal	205
13	internet	505	ability	1167	part	204
14	mobile	496	financial	1148	threats	201
15	inventory	479	revenue	1028	cost	197
16	internal	421	significant	991	competitive	197
17	parties	416	adversely	961	budget	186
18	united	406	information	914	annual	177
19	privacy	397	common	897	obtain	176
20	engagement	397	laws	886	lockheed	176
21	states	386	use	884	spending	176
22	international	384	growth	878	requirements	172
23	twitter	372	operations	852	digimarc	166
24	change	368	changes	834	liability	166
25	software	362	customers	819	include	161
26	expect	357	technology	810	years	159
27	stockholders	351	market	809	agreement	158
28	reporting	348	also	807	delays	158
29	features	347	companies	804	patents	155
30	protection	338	costs	794	year	155
31	effective	337	property	790	prospects	148
32	harmed	326	addition	776	generally	146
33	brand	324	subject	774	funding	146
34	countries	319	affect	767	patent	144
35	practices	317	time	753	levels	144
36	devices	317	employees	751	debt	142
37	rate	312	intellectual	747	contractual	142
38	service	303	rights	715	estimates	142
39	shares	303	continue	698	report	142
40	foreign	302	tax	697	Martin	141
41	negatively	301	able	692	financing	141
42	base	299	certain	686	impairment	141
43	online	297	solutions	676	losses	141
44	source	297	risks	674	current	138
45	decline	295	security	656	insurance	136
46	credit	291	impact	656	depend	136
47	securities	286	control	650	meet	136
48	example	286	increase	648	perform	135
49	regulatory	285	performance	632	inc	135
50	fluctuations	284	regulations	631	expected	134

‘H-word’ keywords occurring only in the top three companies of CAGR of revenue, ‘Inter-word’ keywords occurring in the corpus of both, ‘L-word’ keywords occurring only in the three companies with the lowest CAGR values
^※The TF-IDF value generally includes sub-decimal values, but only the integer value is represented in this table

Back to article page