Method and Results:

In this paper we are going to construct four themes – hydrogen, water, clean energy, and ocean sustainability- using LSA.

First, use Russell 3000 base universe and go through all databases to find available documents within last 9 months that have keyword "hydrogen", controlling the length of target text to be of ideal number of words. There are 2786 records generated from a wide array of document sources including  'MCT', 'DJNS', 'BW', 'FCIS', 'SA', 'BAML', 'GNW', 'AWF', 'EDG', 'DJBT', 'DGAP', 'PRN', 'DJCM', 'TWTR', 'SDR', 'FBLK', 'EDGSEC',  'FT', 'FCST', 'DJCS', 'MTNA', 'DJPR', 'PRNE', 'FCSTEV', 'RSDAM',  'DJES', 'DJGQ', 'FFR', 'WSJ', 'CRN', 'PRNA', 'TDN', 'AWP', 'ASX', 'MTEMEA', 'BRF', 'ACW', 'AFP', 'IA', 'ECMT', 'FSWA', 'SW', 'FFW', 'AFPE', 'RJ', 'DJIN', 'OMX', 'CNW', 'RF', 'FINW', 'FGP', 'AWG', 'PNCV', 'NAR'.

Take the first document for example, “‘particular has seemed to be focused on electric and hydrogen technology. Boeing, on the other hand, have recently that the use of electric or hybrid technology or hydrogen technology in the mainline aircraft, the bread’

A is the document to term/word matrix, A*At is the word/term to term matrix;

while At*A is the document to document matrix

And this is the word/term matrix

After cleansing it removing repetitive stop words, this text is converted to ‘particular seemed focused electric hydrogen technology boeing hand recentlythat use electric hybrid technology hydrogen technology mainline aircraft bread’.

After vectorizing the corpora of these documents, we formed a large-scale matrix with a shape of (2786, 12527). After applying the SVD computation, we set the parameter to be top 3 topics/features,

Further, to know what this top topic or feature is

While topic 2 are composed of different set of words:

Now we have the ranking of every document, which is associated to a company, next, we need to identify the most relevant company accordingly. Since some documents are related to multiple stocks/companies, we remove them only keep document pointing to single stock. Additionally, we found FCST (transcript database) brought back the most number of documents(250), so we filter only FCST sourced documents for each company, take average of their topic score, keep those with topic1 score is equal or greater than the (mean-standard deviation) value, we obtained a US hydrogen portfolio (market cap >= $300m):

Id	Date	p_symbol	p_symbol.1	p_symbol.2	ff_co_name	p_market_val_sec	p_exchange	adtv	topic_1
PLUG-US	2/22/2021	US72919P2020	2508386	PLUG-US	Plug Power, Inc.	28085.7	NAS	1851	0.478346
FCEL-US	2/22/2021	US35952H6018	BK6S6J8	FCEL-US	FuelCell Energy, Inc.	6519.221	NAS	790.9532	0.475276
APD-US	2/22/2021	US0091581068	2011602	APD-US	Air Products & Chemicals, Inc.	58390.55	NYS	329.0846	0.413747
BE-US	2/22/2021	US0937121079	BDD1BB8	BE-US	Bloom Energy Corp.	4431.369	NYS	162.7563	0.394135
NJR-US	2/22/2021	US6460251068	2630513	NJR-US	New Jersey Resources Corp.	3811.517	NYS	19.25094	0.374612
GTLS-US	2/22/2021	US16115Q3083	B19HNF4	GTLS-US	Chart Industries, Inc.	4832.831	NYS	44.40889	0.36377
ATI-US	2/22/2021	US01741R1023	2526117	ATI-US	Allegheny Technologies, Inc.	2457.702	NYS	26.81174	0.352432
LIN-US	2/22/2021	IE00BZ12WP82	BZ12WP8	LIN-US	Linde Plc	131676.1	NYS	412.1747	0.348215
DUK-US	2/22/2021	US26441C2044	B7VD3F2	DUK-US	Duke Energy Corp.	68002.67	NYS	247.3141	0.331449
PCAR-US	2/22/2021	US6937181088	2665861	PCAR-US	PACCAR, Inc.	33024.91	NAS	147.4911	0.319731
LXFR-US	2/22/2021	GB00BNK03D49	BF5GRT5	LXFR-US	Luxfer Holdings Plc	515.4283	NYS	1.548303	0.314576
BKR-US	2/22/2021	US05722G1004	BDHLTQ5	BKR-US	Baker Hughes Co.	16048.12	NYS	126.2361	0.299677
WMB-US	2/22/2021	US9694571004	2967181	WMB-US	The Williams Cos., Inc.	27475.58	NYS	184.6594	0.279647
CMI-US	2/22/2021	US2310211063	2240202	CMI-US	Cummins, Inc.	36522.11	NYS	242.0975	0.279477
SRE-US	2/22/2021	US8168511090	2138158	SRE-US	Sempra Energy	37651.45	NYS	190.3979	0.278915
NEE-US	2/22/2021	US65339F1012	2328915	NEE-US	NextEra Energy, Inc.	153066.2	NYS	554.4232	0.277359
CF-US	2/22/2021	US1252691001	B0G4K50	CF-US	CF Industries Holdings, Inc.	9792.64	NYS	90.93523	0.276364
KBR-US	2/22/2021	US48242W1062	B1HHB18	KBR-US	KBR, Inc.	4597.922	NYS	33.57774	0.265426
WEC-US	2/22/2021	US92939U1060	BYY8XK8	WEC-US	WEC Energy Group, Inc.	26253.62	NYS	110.1452	0.264127
EMR-US	2/22/2021	US2910111044	2313405	EMR-US	Emerson Electric Co.	51272.54	NYS	203.0424	0.263428
AGR-US	2/22/2021	US05351W1036	BYP0CD9	AGR-US	Avangrid, Inc.	13930.19	NYS	27.29743	0.255663
MTRX-US	2/22/2021	US5768531056	2572068	MTRX-US	Matrix Service Co.	346.2235	NAS	2.937673	0.255432
RUSHA-US	2/22/2021	US7818462092	2966876	RUSHA-US	Rush Enterprises, Inc.	1750.737	NAS	8.177229	0.252914
KMI-US	2/22/2021	US49456B1017	B3NQ4P8	KMI-US	Kinder Morgan, Inc.	33866.36	NYS	245.7693	0.24455
OGS-US	2/22/2021	US68235P1084	BJ0KXV4	OGS-US	ONE Gas, Inc.	3932.356	NYS	18.44767	0.240674
PSX-US	2/22/2021	US7185461040	B78C4Y8	PSX-US	Phillips 66	35953.02	NYS	205.9026	0.238571
DAN-US	2/22/2021	US2358252052	B2PFJR3	DAN-US	Dana, Inc.	3223.261	NYS	26.26979	0.238432
DOV-US	2/22/2021	US2600031080	2278407	DOV-US	Dover Corp.	17561.12	NYS	85.92194	0.217643
BEPC-US	2/22/2021	CA11284V1058	BMW8YT2	BEPC-US	Brookfield Renewable Corp.	8469.609	NYS	44.28724	0.217028
XOM-US	2/22/2021	US30231G1022	2326618	XOM-US	Exxon Mobil Corp.	221682.2	NYS	1212.771	0.216212
SLB-US	2/22/2021	AN8068571086	2779201	SLB-US	Schlumberger NV	36367.56	NYS	281.7826	0.215069
AZPN-US	2/22/2021	US0453271035	2051868	AZPN-US	Aspen Technology, Inc.	10537.36	NAS	51.47538	0.21272
TSLA-US	2/22/2021	US88160R1014	B616C79	TSLA-US	Tesla, Inc.	749933.5	NAS	26729.57	0.207524
HY-US	2/22/2021	US4491721050	B7LG306	HY-US	Hyster-Yale Materials Handling, Inc.	1246.51	NYS	5.977456	0.207209
NFG-US	2/22/2021	US6361801011	2626103	NFG-US	National Fuel Gas Co.	4144.29	NYS	18.88197	0.199536
LAZ-US	2/22/2021	BMG540501027	B081VQ7	LAZ-US	Lazard Ltd.	4641.453	NYS	27.89917	0.199406
ATO-US	2/22/2021	US0495601058	2315359	ATO-US	Atmos Energy Corp.	11990.71	NYS	90.41402	0.195311
J-US	2/22/2021	US4698141078	2469052	J-US	Jacobs Engineering Group, Inc.	14622.99	NYS	67.32813	0.194618
SJI-US	2/22/2021	US8385181081	2825933	SJI-US	South Jersey Industries, Inc.	2440.321	NYS	19.19488	0.190869
CC-US	2/22/2021	US1638511089	BZ0CTP8	CC-US	The Chemours Co.	4286.212	NYS	29.73314	0.189885
CAT-US	2/22/2021	US1491231015	2180201	CAT-US	Caterpillar, Inc.	114464.7	NYS	510.4117	0.188521
CMS-US	2/22/2021	US1258961002	2219224	CMS-US	CMS Energy Corp.	16175.05	NYS	99.26598	0.186496
OKE-US	2/22/2021	US6826801036	2130109	OKE-US	ONEOK, Inc.	20362.29	NYS	119.0931	0.186074
VLO-US	2/22/2021	US91913Y1001	2041364	VLO-US	Valero Energy Corp.	29169.16	NYS	224.5973	0.185284
XEL-US	2/22/2021	US98389B1008	2614807	XEL-US	Xcel Energy, Inc.	33371.86	NAS	154.8865	0.185053
RTX-US	2/22/2021	US75513E1010	BM5M5Y3	RTX-US	Raytheon Technologies Corp.	112836.4	NYS	459.6514	0.178425
NWN-US	2/22/2021	US66765N1054	BFNR303	NWN-US	Northwest Natural Holding Co.	1494.192	NYS	14.11395	0.178126
ETR-US	2/22/2021	US29364G1031	2317087	ETR-US	Entergy Corp.	18657.67	NYS	128.1704	0.176371
GM-US	2/22/2021	US37045V1008	B665KZ5	GM-US	General Motors Co.	75748.79	NYS	991.4799	0.171622
AMRC-US	2/22/2021	US02361E1082	B3SWPT2	AMRC-US	Ameresco, Inc.	1919.791	NYS	22.21005	0.167686
ETN-US	2/22/2021	IE00B8KQN827	B8KQN82	ETN-US	Eaton Corp. Plc	50941.08	NYS	228.1494	0.162775
HON-US	2/22/2021	US4385161066	2020459	HON-US	Honeywell International, Inc.	141576.2	NYS	518.0762	0.160773
CNP-US	2/22/2021	US15189T1079	2440637	CNP-US	CenterPoint Energy, Inc.	11675.52	NYS	95.8031	0.158457
ALSN-US	2/22/2021	US01973R1014	B4PZ892	ALSN-US	Allison Transmission Holdings, Inc.	4269.581	NYS	37.74042	0.157128
NOV-US	2/22/2021	US62955J1034	BN2RYW9	NOV-US	NOV, Inc.	5446.604	NYS	70.77102	0.156641
CVX-US	2/22/2021	US1667641005	2838555	CVX-US	Chevron Corp.	184420	NYS	856.6611	0.156143
WAB-US	2/22/2021	US9297401088	2955733	WAB-US	Westinghouse Air Brake Technologies Corp.	13970.75	NYS	81.67142	0.155003
BA-US	2/22/2021	US0970231058	2108601	BA-US	The Boeing Co.	126784.3	NYS	3091.603	0.154109
NEM-US	2/22/2021	US6516391066	2636607	NEM-US	Newmont Corp.	45353.81	NYS	355.104	0.15371
CMCO-US	2/22/2021	US1993331057	2211071	CMCO-US	Columbus McKinnon Corp.	1149.692	NAS	3.30757	0.153693
LAD-US	2/22/2021	US5367971034	2515030	LAD-US	Lithia Motors, Inc.	10062.54	NYS	85.05016	0.151705
IR-US	2/22/2021	US45687V1061	BL5GZ82	IR-US	Ingersoll Rand, Inc.	18330.91	NYS	75.64819	0.149595
FLT-US	2/22/2021	US3390411052	B4R28B3	FLT-US	FLEETCOR Technologies, Inc.	22872.66	NYS	158.864	0.147923
FLS-US	2/22/2021	US34354P1057	2288406	FLS-US	Flowserve Corp.	5111.537	NYS	28.42058	0.14479
DCI-US	2/22/2021	US2576511099	2276467	DCI-US	Donaldson Co., Inc.	7705.685	NYS	26.48534	0.140336
UGI-US	2/22/2021	US9026811052	2910118	UGI-US	UGI Corp.	8402.635	NYS	33.49469	0.139997
GE-US	2/22/2021	US3696041033	2380498	GE-US	General Electric Co.	105390.7	NYS	821.6511	0.139869
HAYN-US	2/22/2021	US4208772016	B02WVH7	HAYN-US	Haynes International, Inc.	369.8114	NAS	2.684321	0.137949
SR-US	2/22/2021	US84857L1017	BYXJQG9	SR-US	Spire Inc.	3496.14	NYS	19.32382	0.136633
THR-US	2/22/2021	US88362T1034	B3N6F00	THR-US	Thermon Group Holdings, Inc.	592.5712	NYS	2.325063	0.130383
FLR-US	2/22/2021	US3434121022	2696838	FLR-US	Fluor Corp.	2434.373	NYS	31.81162	0.129712
SNDR-US	2/22/2021	US80689H1023	BYVN953	SNDR-US	Schneider National, Inc.	2210.975	NYS	12.60489	0.128699
NI-US	2/22/2021	US65473P1057	2645409	NI-US	NiSource, Inc.	8950.076	NYS	60.86271	0.126539
AES-US	2/22/2021	US00130H1059	2002479	AES-US	The AES Corp.	18829.86	NYS	144.5494	0.119861
TPIC-US	2/22/2021	US87266J1043	BYYGK12	TPIC-US	TPI Composites, Inc.	2519.726	NAS	41.5175	0.11437
SO-US	2/22/2021	US8425871071	2829601	SO-US	The Southern Co.	62667.52	NYS	201.1552	0.114074
ENS-US	2/22/2021	US29275Y1029	B020GQ5	ENS-US	EnerSys	3898.603	NYS	19.74859	0.113874
WERN-US	2/22/2021	US9507551086	2948852	WERN-US	Werner Enterprises, Inc.	2955.709	NAS	23.46665	0.108954
ADM-US	2/22/2021	US0394831020	2047317	ADM-US	Archer-Daniels-Midland Co.	31338.2	NYS	117.7202	0.10666
ASPN-US	2/22/2021	US04523Y1055	BN65SM7	ASPN-US	Aspen Aerogels, Inc.	638.6505	NYS	4.75875	0.104615
HASI-US	2/22/2021	US41068X1000	B9HHD96	HASI-US	Hannon Armstrong Sustainable Infrastructure Capital, Inc.	4847.081	NYS	43.0033	0.10375
PBF-US	2/22/2021	US69318G1067	B7F4TJ7	PBF-US	PBF Energy, Inc.	1623.798	NYS	51.75431	0.103303
GTES-US	2/22/2021	GB00BD9G2S12	BD9G2S1	GTES-US	Gates Industrial Corp. Plc	4941.593	NYS	3.351595	0.101966
EQIX-US	2/22/2021	US29444U7000	BVLZX12	EQIX-US	Equinix, Inc.	60735.38	NAS	343.933	0.101727
IDA-US	2/22/2021	US4511071064	2296937	IDA-US	IDACORP, Inc.	4450.377	NYS	27.23598	0.100936
TT-US	2/22/2021	IE00BK9ZQ967	BK9ZQ96	TT-US	Trane Technologies Plc	36708.48	NYS	173.7251	0.098733
ACM-US	2/22/2021	US00766T1007	B1VZ431	ACM-US	AECOM	8443.192	NYS	55.0099	0.09789
REVG-US	2/22/2021	US7495271071	BDRW1P1	REVG-US	REV Group, Inc.	784.92	NYS	2.723662	0.097737
MDU-US	2/22/2021	US5526901096	2547323	MDU-US	MDU Resources Group, Inc.	5698.835	NYS	23.49703	0.097626
SPGI-US	2/22/2021	US78409V1044	BYV2325	SPGI-US	S&P Global, Inc.	81655.06	NYS	546.5309	0.097095
PWR-US	2/22/2021	US74762E1029	2150204	PWR-US	Quanta Services, Inc.	10727.01	NYS	77.158	0.094897
INFO-US	2/22/2021	BMG475671050	BD0Q558	INFO-US	IHS Markit Ltd.	36962.36	NYS	285.4182	0.094232
DOW-US	2/22/2021	US2605571031	BHXCF84	DOW-US	Dow, Inc.	44925	NYS	206.1239	0.093536
REGI-US	2/22/2021	US75972A3014	B7577T2	REGI-US	Renewable Energy Group, Inc.	3813.307	NAS	84.50222	0.09342
CVI-US	2/22/2021	US12662P1084	B23PS12	CVI-US	CVR Energy, Inc.	2302.151	NYS	9.393456	0.091302
WTRG-US	2/22/2021	US29670G1022	BLCF3J9	WTRG-US	Essential Utilities, Inc.	11177.03	NYS	46.77527	0.091217
CLF-US	2/22/2021	US1858991011	BYVZ186	CLF-US	Cleveland-Cliffs, Inc.	8490.291	NYS	210.6924	0.090391
WOR-US	2/22/2021	US9818111026	2981932	WOR-US	Worthington Industries, Inc.	3294.414	NYS	13.30405	0.090075
MPC-US	2/22/2021	US56585A1025	B3K3L40	MPC-US	Marathon Petroleum Corp.	34503	NYS	253.6227	0.08948
VNT-US	2/22/2021	US9288811014	BH4GV32	VNT-US	Vontier Corp.	5284.069	NYS	81.30291	0.088447
MTZ-US	2/22/2021	US5763231090	2155306	MTZ-US	MasTec, Inc.	6343.693	NYS	52.90216	0.088215
OLN-US	2/22/2021	US6806652052	2658526	OLN-US	Olin Corp.	4732.704	NYS	33.21598	0.086323
MNR-US	2/22/2021	US6097201072	2504072	MNR-US	Monmouth Real Estate Investment Corp.	1758.598	NYS	9.651529	0.084795

Next, we’d try the same method on Korean stock market.